Search Results for author: Irwin King

Found 134 papers, 60 papers with code

An Entropy-based Text Watermarking Detection Method

no code implementations20 Mar 2024 Yijian Lu, Aiwei Liu, Dianzhi Yu, Jingjing Li, Irwin King

In this work, we proposed that the influence of token entropy should be fully considered in the watermark detection process, that is, the weight of each token should be adjusted according to its entropy during watermark detection, rather than setting the weight of all tokens to the same value as in previous methods.

CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models

1 code implementation6 Mar 2024 Zexuan Qiu, Jingjing Li, Shijue Huang, Wanjun Zhong, Irwin King

Developing Large Language Models (LLMs) with robust long-context capabilities has been the recent research focus, resulting in the emergence of long-context LLMs proficient in Chinese.

Progress and Opportunities of Foundation Models in Bioinformatics

no code implementations6 Feb 2024 Qing Li, Zhihang Hu, YiXuan Wang, Lei LI, Yimin Fan, Irwin King, Le Song, Yu Li

Central to our focus is the application of FMs to specific biological problems, aiming to guide the research community in choosing appropriate FMs for their research needs.

HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval

no code implementations14 Jan 2024 Zexuan Qiu, Jiahong Liu, Yankai Chen, Irwin King

Existing unsupervised deep product quantization methods primarily aim for the increased similarity between different views of the identical image, whereas the delicate multi-level semantic similarities preserved between images are overlooked.

Contrastive Learning Image Retrieval +4

A Survey of Text Watermarking in the Era of Large Language Models

no code implementations13 Dec 2023 Aiwei Liu, Leyi Pan, Yijian Lu, Jingjing Li, Xuming Hu, Xi Zhang, Lijie Wen, Irwin King, Hui Xiong, Philip S. Yu

Text watermarking algorithms play a crucial role in the copyright protection of textual content, yet their capabilities and application scenarios have been limited historically.

Dialogue Generation

Generalized Category Discovery with Clustering Assignment Consistency

no code implementations30 Oct 2023 Xiangli Yang, Xinglin Pan, Irwin King, Zenglin Xu

To address the GCD without knowing the class number of unlabeled dataset, we propose a co-training-based framework that encourages clustering consistency.

Clustering Community Detection +2

Alignment and Outer Shell Isotropy for Hyperbolic Graph Contrastive Learning

no code implementations27 Oct 2023 Yifei Zhang, Hao Zhu, Jiahong Liu, Piotr Koniusz, Irwin King

We show that in the hyperbolic space one has to address the leaf- and height-level uniformity which are related to properties of trees, whereas in the ambient space of the hyperbolic manifold, these notions translate into imposing an isotropic ring density towards boundaries of Poincar\'e ball.

Contrastive Learning Graph Embedding +1

Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue

no code implementations13 Oct 2023 Hongru Wang, Minda Hu, Yang Deng, Rui Wang, Fei Mi, Weichao Wang, Yasheng Wang, Wai-Chung Kwan, Irwin King, Kam-Fai Wong

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses.

Response Generation

Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?

no code implementations29 Aug 2023 Jingyan Zhou, Minda Hu, Junan Li, Xiaoying Zhang, Xixin Wu, Irwin King, Helen Meng

Our analysis exhibits the potentials and flaws in existing resources (models and datasets) in developing explainable moral judgment-making systems.

Ethics

An Unforgeable Publicly Verifiable Watermark for Large Language Models

2 code implementations30 Jul 2023 Aiwei Liu, Leyi Pan, Xuming Hu, Shu'ang Li, Lijie Wen, Irwin King, Philip S. Yu

Experiments demonstrate that our algorithm attains high detection accuracy and computational efficiency through neural networks with a minimized number of parameters.

Computational Efficiency

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

1 code implementation7 Jul 2023 Ming Jin, Huan Yee Koh, Qingsong Wen, Daniele Zambon, Cesare Alippi, Geoffrey I. Webb, Irwin King, Shirui Pan

In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation.

Anomaly Detection Imputation +2

A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges

no code implementations28 Jun 2023 Ziqiao Meng, Peilin Zhao, Yang Yu, Irwin King

Reaction and retrosynthesis prediction are fundamental tasks in computational chemistry that have recently garnered attention from both the machine learning and drug discovery communities.

Drug Discovery Retrosynthesis

Hyperbolic Representation Learning: Revisiting and Advancing

1 code implementation15 Jun 2023 Menglin Yang, Min Zhou, Rex Ying, Yankai Chen, Irwin King

To address this, we propose a simple yet effective method, hyperbolic informed embedding (HIE), by incorporating cost-free hierarchical information deduced from the hyperbolic distance of the node to origin (i. e., induced hyperbolic norm) to advance existing \hlms.

Representation Learning

Doubly Stochastic Graph-based Non-autoregressive Reaction Prediction

no code implementations5 Jun 2023 Ziqiao Meng, Peilin Zhao, Yang Yu, Irwin King

However, the current non-autoregressive decoder does not satisfy two essential rules of electron redistribution modeling simultaneously: the electron-counting rule and the symmetry rule.

Drug Discovery

Exploring semantic information in disease: Simple Data Augmentation Techniques for Chinese Disease Normalization

no code implementations2 Jun 2023 Wenqian Cui, Xiangling Fu, Shaohui Liu, Mingjun Gu, Xien Liu, Ji Wu, Irwin King

Nevertheless, the most significant obstacle to existing disease name normalization systems is the severe shortage of training data.

Data Augmentation

GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks

no code implementations26 May 2023 Xuming Hu, Aiwei Liu, Zeqi Tan, Xin Zhang, Chenwei Zhang, Irwin King, Philip S. Yu

These techniques neither preserve the semantic consistency of the original sentences when rule-based augmentations are adopted, nor preserve the syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations.

Data Augmentation Relation +1

Multimodal Relation Extraction with Cross-Modal Retrieval and Synthesis

no code implementations25 May 2023 Xuming Hu, Zhijiang Guo, Zhiyang Teng, Irwin King, Philip S. Yu

Multimodal relation extraction (MRE) is the task of identifying the semantic relationships between two entities based on the context of the sentence image pair.

Cross-Modal Retrieval Object +4

Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction

1 code implementation2 May 2023 Xuming Hu, Zhaochen Hong, Chenwei Zhang, Irwin King, Philip S. Yu

Relation extraction (RE) aims to extract potential relations according to the context of two entities, thus, deriving rational contexts from sentences plays an important role.

counterfactual Relation +2

Bipartite Graph Convolutional Hashing for Effective and Efficient Top-N Search in Hamming Space

no code implementations1 Apr 2023 Yankai Chen, Yixiang Fang, Yifei Zhang, Irwin King

We propose an end-to-end Bipartite Graph Convolutional Hashing approach, namely BGCH, which consists of three novel and effective modules: (1) adaptive graph convolutional hashing, (2) latent feature dispersion, and (3) Fourier serialized gradient estimation.

Retrieval

Knowledge Transfer via Multi-Head Feature Adaptation for Whole Slide Image Classification

no code implementations10 Mar 2023 Conghao Xiong, Yi Lin, Hao Chen, Joseph Sung, Irwin King

Transferring prior knowledge from a source domain to the same or similar target domain can greatly enhance the performance of models on the target domain.

Classification Image Classification +1

Drug Synergistic Combinations Predictions via Large-Scale Pre-Training and Graph Structure Learning

no code implementations14 Jan 2023 Zhihang Hu, Qinze Yu, Yucheng Guo, Taifeng Wang, Irwin King, Xin Gao, Le Song, Yu Li

While previous methods reported fair performance, their models usually do not take advantage of multi-modal data and they are unable to handle new drugs or cell lines.

Graph structure learning

Momentum Contrastive Pre-training for Question Answering

no code implementations12 Dec 2022 Minda Hu, Muzhi Li, Yasheng Wang, Irwin King

In order to address this problem, we propose a novel Momentum Contrastive pRe-training fOr queStion anSwering (MCROSS) method for extractive QA.

Benchmarking Contrastive Learning +3

kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learning

no code implementations4 Dec 2022 Menglin Yang, Min Zhou, Lujia Pan, Irwin King

The prevalence of tree-like structures, encompassing hierarchical structures and power law distributions, exists extensively in real-world applications, including recommendation systems, ecosystems, financial networks, social networks, etc.

Link Prediction Node Classification +2

Spectral Feature Augmentation for Graph Contrastive Learning and Beyond

no code implementations2 Dec 2022 Yifei Zhang, Hao Zhu, Zixing Song, Piotr Koniusz, Irwin King

Although augmentations (e. g., perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible, complementary yet not well researched strategy.

Contrastive Learning

MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks

1 code implementation23 Nov 2022 Xinyu Fu, Irwin King

Heterogeneous graph neural networks (HGNNs) were proposed for representation learning on structural data with multiple types of nodes and edges.

Computational Efficiency Link Prediction +2

Hyperbolic Graph Representation Learning: A Tutorial

no code implementations8 Nov 2022 Min Zhou, Menglin Yang, Lujia Pan, Irwin King

We first give a brief introduction to graph representation learning as well as some preliminary Riemannian and hyperbolic geometry.

Graph Learning Graph Representation Learning +2

Knowledge-aware Neural Networks with Personalized Feature Referencing for Cold-start Recommendation

no code implementations28 Sep 2022 Xinni Zhang, Yankai Chen, Cuiyun Gao, Qing Liao, Shenglin Zhao, Irwin King

Incorporating knowledge graphs (KGs) as side information in recommendation has recently attracted considerable attention.

Knowledge Graphs

HICF: Hyperbolic Informative Collaborative Filtering

1 code implementation19 Jul 2022 Menglin Yang, Zhihao LI, Min Zhou, Jiahong Liu, Irwin King

The results reveal that (1) tail items get more emphasis in hyperbolic space than that in Euclidean space, but there is still ample room for improvement; (2) head items receive modest attention in hyperbolic space, which could be considerably improved; (3) and nonetheless, the hyperbolic models show more competitive performance than Euclidean models.

Collaborative Filtering Recommendation Systems

Graph Component Contrastive Learning for Concept Relatedness Estimation

1 code implementation25 Jun 2022 Yueen Ma, Zixing Song, Xuming Hu, Jingjing Li, Yifei Zhang, Irwin King

As it is intractable for data augmentation to fully capture the structural information of the ConcreteGraph due to a large amount of potential concept pairs, we further introduce a novel Graph Component Contrastive Learning framework to implicitly learn the complete structure of the ConcreteGraph.

Contrastive Learning Data Augmentation +2

ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization

no code implementations16 Jun 2022 Langzhang Liang, Zenglin Xu, Zixing Song, Irwin King, Jieping Ye

In detail, by studying the long-tailed distribution of node degrees in the graph, we propose a novel normalization method for GNNs, which is termed ResNorm (\textbf{Res}haping the long-tailed distribution into a normal-like distribution via \textbf{norm}alization).

Node Classification

COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning

1 code implementation9 Jun 2022 Yifei Zhang, Hao Zhu, Zixing Song, Piotr Koniusz, Irwin King

In this paper, we show that the node embedding obtained via the graph augmentations is highly biased, somewhat limiting contrastive models from learning discriminative features for downstream tasks.

Contrastive Learning Graph Representation Learning

Encoded Gradients Aggregation against Gradient Leakage in Federated Learning

no code implementations26 May 2022 Dun Zeng, Shiyu Liu, Siqi Liang, Zonghang Li, Hui Wang, Irwin King, Zenglin Xu

However, privacy information could be leaked from uploaded gradients and be exposed to malicious attackers or an honest-but-curious server.

Federated Learning

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

1 code implementation18 Apr 2022 Menglin Yang, Min Zhou, Jiahong Liu, Defu Lian, Irwin King

Hyperbolic space offers a spacious room to learn embeddings with its negative curvature and metric properties, which can well fit data with tree-like structures.

Collaborative Filtering Recommendation Systems

Text Revision by On-the-Fly Representation Optimization

1 code implementation In2Writing (ACL) 2022 Jingjing Li, Zichao Li, Tao Ge, Irwin King, Michael R. Lyu

In this approach, we simply fine-tune a pre-trained Transformer with masked language modeling and attribute classification.

Attribute Language Modelling +3

Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions

1 code implementation1 Apr 2022 Jiayang Chen, Zhihang Hu, Siqi Sun, Qingxiong Tan, YiXuan Wang, Qinze Yu, Licheng Zong, Liang Hong, Jin Xiao, Tao Shen, Irwin King, Yu Li

Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations.

Self-Supervised Learning

Hyperbolic Graph Neural Networks: A Review of Methods and Applications

1 code implementation28 Feb 2022 Menglin Yang, Min Zhou, Zhihao LI, Jiahong Liu, Lujia Pan, Hui Xiong, Irwin King

Graph neural networks generalize conventional neural networks to graph-structured data and have received widespread attention due to their impressive representation ability.

Anatomy Graph Learning

CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs

no code implementations16 Feb 2022 Feng Xia, Lei Wang, Tao Tang, Xin Chen, Xiangjie Kong, Giles Oatley, Irwin King

In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices.

Link Prediction

Graph-adaptive Rectified Linear Unit for Graph Neural Networks

no code implementations13 Feb 2022 Yifei Zhang, Hao Zhu, Ziqiao Meng, Piotr Koniusz, Irwin King

However, in the updating stage, all nodes share the same updating function.

Towards Efficient Post-training Quantization of Pre-trained Language Models

no code implementations30 Sep 2021 Haoli Bai, Lu Hou, Lifeng Shang, Xin Jiang, Irwin King, Michael R. Lyu

Experiments on GLUE and SQuAD benchmarks show that our proposed PTQ solution not only performs close to QAT, but also enjoys significant reductions in training time, memory overhead, and data consumption.

Quantization

Multimodality in Meta-Learning: A Comprehensive Survey

no code implementations28 Sep 2021 Yao Ma, Shilin Zhao, Weixiao Wang, Yaoman Li, Irwin King

This survey provides a comprehensive overview of the multimodality-based meta-learning landscape in terms of the methodologies and applications.

Few-Shot Learning Zero-Shot Learning

Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation

no code implementations5 Sep 2021 Yankai Chen, Yaming Yang, Yujing Wang, Jing Bai, Xiangchen Song, Irwin King

However, simply integrating KGs in current KG-based RS models is not necessarily a guarantee to improve the recommendation performance, which may even weaken the holistic model capability.

Click-Through Rate Prediction Knowledge-Aware Recommendation +1

Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation

no code implementations14 Aug 2021 Yankai Chen, Menglin Yang, Yingxue Zhang, Mengchen Zhao, Ziqiao Meng, Jianye Hao, Irwin King

Aiming to alleviate data sparsity and cold-start problems of traditional recommender systems, incorporating knowledge graphs (KGs) to supplement auxiliary information has recently gained considerable attention.

Knowledge-Aware Recommendation Knowledge Graphs

Controllable Summarization with Constrained Markov Decision Process

1 code implementation7 Aug 2021 Hou Pong Chan, Lu Wang, Irwin King

We study controllable text summarization which allows users to gain control on a particular attribute (e. g., length limit) of the generated summaries.

Attribute Text Summarization

Dialogue Summarization with Supporting Utterance Flow Modeling and Fact Regularization

1 code implementation3 Aug 2021 Wang Chen, Piji Li, Hou Pong Chan, Irwin King

The supporting utterance flow modeling helps to generate a coherent summary by smoothly shifting the focus from the former utterances to the later ones.

Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space

1 code implementation8 Jul 2021 Menglin Yang, Min Zhou, Marcus Kalander, Zengfeng Huang, Irwin King

To explore these properties of a complex temporal network, we propose a hyperbolic temporal graph network (HTGN) that fully takes advantage of the exponential capacity and hierarchical awareness of hyperbolic geometry.

Graph Embedding Link Prediction +1

Improving the Transferability of Adversarial Samples With Adversarial Transformations

1 code implementation CVPR 2021 Weibin Wu, Yuxin Su, Michael R. Lyu, Irwin King

Although deep neural networks (DNNs) have achieved tremendous performance in diverse vision challenges, they are surprisingly susceptible to adversarial examples, which are born of intentionally perturbing benign samples in a human-imperceptible fashion.

A Condense-then-Select Strategy for Text Summarization

1 code implementation19 Jun 2021 Hou Pong Chan, Irwin King

This framework first selects salient sentences and then independently condenses each of the selected sentences into a concise version.

Sentence Text Summarization

Discrete Auto-regressive Variational Attention Models for Text Modeling

1 code implementation16 Jun 2021 Xianghong Fang, Haoli Bai, Jian Li, Zenglin Xu, Michael Lyu, Irwin King

We further design discrete latent space for the variational attention and mathematically show that our model is free from posterior collapse.

Language Modelling

Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation

no code implementations8 Jun 2021 Pengpeng Liu, Michael R. Lyu, Irwin King, Jia Xu

Then, a self-supervised learning framework is constructed: confident predictions from teacher models are served as annotations to guide the student model to learn optical flow for those less confident predictions.

Knowledge Distillation Optical Flow Estimation +1

Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation

1 code implementation ACL 2021 Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Shuming Shi, Michael R. Lyu, Irwin King

In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data.

Machine Translation NMT +1

A Survey on Deep Semi-supervised Learning

no code implementations28 Feb 2021 Xiangli Yang, Zixing Song, Irwin King, Zenglin Xu

Deep semi-supervised learning is a fast-growing field with a range of practical applications.

FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding

1 code implementation27 Feb 2021 Menglin Yang, Ziqiao Meng, Irwin King

As a matter of fact, this smoothing technique can not only encourage must-link node pairs to get closer but also push cannot-link pairs to shrink together, which potentially cause serious feature shrink or oversmoothing problem, especially when stacking graph convolution in multiple layers or steps.

Dynamic graph embedding

Graph-based Semi-supervised Learning: A Comprehensive Review

1 code implementation26 Feb 2021 Zixing Song, Xiangli Yang, Zenglin Xu, Irwin King

An important class of SSL methods is to naturally represent data as graphs such that the label information of unlabelled samples can be inferred from the graphs, which corresponds to graph-based semi-supervised learning (GSSL) methods.

Graph Embedding

Open-Retrieval Conversational Machine Reading

1 code implementation17 Feb 2021 Yifan Gao, Jingjing Li, Chien-Sheng Wu, Michael R. Lyu, Irwin King

On our created OR-ShARC dataset, MUDERN achieves the state-of-the-art performance, outperforming existing single-passage conversational machine reading models as well as a new multi-passage conversational machine reading baseline by a large margin.

Discourse Segmentation Reading Comprehension +1

Creation and Evaluation of a Pre-tertiary Artificial Intelligence (AI) Curriculum

no code implementations19 Jan 2021 Thomas K. F. Chiu, Helen Meng, Ching-Sing Chai, Irwin King, Savio Wong, Yeung Yam

Background: AI4Future is a cross-sector project that engages five major partners - CUHK Faculty of Engineering and Faculty of Education, Hong Kong secondary schools, the government and the AI industry.

A Literature Review of Recent Graph Embedding Techniques for Biomedical Data

no code implementations17 Jan 2021 Yankai Chen, Yaozu Wu, Shicheng Ma, Irwin King

With the rapid development of biomedical software and hardware, a large amount of relational data interlinking genes, proteins, chemical components, drugs, diseases, and symptoms has been collected for modern biomedical research.

Graph Embedding

Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings

1 code implementation EMNLP 2020 Yue Wang, Jing Li, Michael R. Lyu, Irwin King

Further analyses show that our multi-head attention is able to attend information from various aspects and boost classification or generation in diverse scenarios.

Effective Data-aware Covariance Estimator from Compressed Data

no code implementations10 Oct 2020 Xixian Chen, Haiqin Yang, Shenglin Zhao, Michael R. Lyu, Irwin King

Estimating covariance matrix from massive high-dimensional and distributed data is significant for various real-world applications.

Making Online Sketching Hashing Even Faster

no code implementations10 Oct 2020 Xixian Chen, Haiqin Yang, Shenglin Zhao, Michael R. Lyu, Irwin King

Data-dependent hashing methods have demonstrated good performance in various machine learning applications to learn a low-dimensional representation from the original data.

Learning 3D Face Reconstruction with a Pose Guidance Network

no code implementations9 Oct 2020 Pengpeng Liu, Xintong Han, Michael Lyu, Irwin King, Jia Xu

We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN).

3D Face Reconstruction Pose Estimation +1

Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation

1 code implementation EMNLP 2020 Wenxiang Jiao, Xing Wang, Shilin He, Irwin King, Michael R. Lyu, Zhaopeng Tu

First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities.

Machine Translation NMT +2

Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading

1 code implementation EMNLP 2020 Yifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq Joty, Steven C. H. Hoi, Caiming Xiong, Irwin King, Michael R. Lyu

Based on the learned EDU and entailment representations, we either reply to the user our final decision "yes/no/irrelevant" of the initial question, or generate a follow-up question to inquiry more information.

Decision Making Discourse Segmentation +3

Emerging App Issue Identification via Online Joint Sentiment-Topic Tracing

no code implementations23 Aug 2020 Cuiyun Gao, Jichuan Zeng, Zhiyuan Wen, David Lo, Xin Xia, Irwin King, Michael R. Lyu

Experiments on popular apps from Google Play and Apple's App Store demonstrate the effectiveness of MERIT in identifying emerging app issues, improving the state-of-the-art method by 22. 3% in terms of F1-score.

Clustering

Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship Mining

no code implementations17 Aug 2020 Jiaying Liu, Feng Xia, Lei Wang, Bo Xu, Xiangjie Kong, Hanghang Tong, Irwin King

The advisor-advisee relationship represents direct knowledge heritage, and such relationship may not be readily available from academic libraries and search engines.

Representation Learning

A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss

1 code implementation2 Jun 2020 Hou Pong Chan, Wang Chen, Irwin King

Review summarization aims at generating a concise summary that describes the key opinions and sentiment of a review, while sentiment classification aims to predict a sentiment label indicating the sentiment attitude of a review.

General Classification Sentiment Analysis +1

EMT: Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading

1 code implementation26 May 2020 Yifan Gao, Chien-Sheng Wu, Shafiq Joty, Caiming Xiong, Richard Socher, Irwin King, Michael R. Lyu, Steven C. H. Hoi

The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.

Decision Making Reading Comprehension +1

VD-BERT: A Unified Vision and Dialog Transformer with BERT

1 code implementation EMNLP 2020 Yue Wang, Shafiq Joty, Michael R. Lyu, Irwin King, Caiming Xiong, Steven C. H. Hoi

By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks.

Answer Generation Visual Dialog

Discrete Variational Attention Models for Language Generation

no code implementations21 Apr 2020 Xianghong Fang, Haoli Bai, Zenglin Xu, Michael Lyu, Irwin King

Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse.

Language Modelling Text Generation

Exclusive Hierarchical Decoding for Deep Keyphrase Generation

1 code implementation ACL 2020 Wang Chen, Hou Pong Chan, Piji Li, Irwin King

A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of keyphrases and simultaneously determine the appropriate number of keyphrases to produce.

Keyphrase Generation

Automating App Review Response Generation

1 code implementation10 Feb 2020 Cuiyun Gao, Jichuan Zeng, Xin Xia, David Lo, Michael R. Lyu, Irwin King

Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app.

Response Generation

What Changed Your Mind: The Roles of Dynamic Topics and Discourse in Argumentation Process

no code implementations10 Feb 2020 Jichuan Zeng, Jing Li, Yulan He, Cuiyun Gao, Michael R. Lyu, Irwin King

In our world with full of uncertainty, debates and argumentation contribute to the progress of science and society.

Persuasiveness

MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

2 code implementations5 Feb 2020 Xinyu Fu, Jiani Zhang, Ziqiao Meng, Irwin King

A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types.

Clustering Graph Embedding +3

Few Shot Network Compression via Cross Distillation

1 code implementation21 Nov 2019 Haoli Bai, Jiaxiang Wu, Irwin King, Michael Lyu

The core challenge of few shot network compression lies in high estimation errors from the original network during inference, since the compressed network can easily over-fits on the few training instances.

Knowledge Distillation Model Compression

Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network

1 code implementation20 Nov 2019 Wenxiang Jiao, Michael R. Lyu, Irwin King

We propose an Attention Gated Hierarchical Memory Network (AGHMN) to address the problems of prior work: (1) Commonly used convolutional neural networks (CNNs) for utterance feature extraction are less compatible in the memory modules; (2) Unidirectional gated recurrent units (GRUs) only allow each historical utterance to have context before it, preventing information propagation in the opposite direction; (3) The Soft Attention for summarizing loses the positional and ordering information of memories, regardless of how the memory bank is built.

Emotion Recognition in Conversation

Improving Word Representations: A Sub-sampled Unigram Distribution for Negative Sampling

no code implementations21 Oct 2019 Wenxiang Jiao, Irwin King, Michael R. Lyu

Word2Vec is the most popular model for word representation and has been widely investigated in literature.

Sentence Sentence Completion

PT-CoDE: Pre-trained Context-Dependent Encoder for Utterance-level Emotion Recognition

1 code implementation20 Oct 2019 Wenxiang Jiao, Michael R. Lyu, Irwin King

Witnessing the success of transfer learning in natural language process (NLP), we propose to pre-train a context-dependent encoder (CoDE) for ULER by learning from unlabeled conversation data.

Emotion Recognition Sentence +3

Improving Question Generation With to the Point Context

no code implementations IJCNLP 2019 Jingjing Li, Yifan Gao, Lidong Bing, Irwin King, Michael R. Lyu

Question generation (QG) is the task of generating a question from a reference sentence and a specified answer within the sentence.

Question Generation Question-Generation +1

Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling

1 code implementation ACL 2019 Yifan Gao, Piji Li, Irwin King, Michael R. Lyu

The coreference alignment modeling explicitly aligns coreferent mentions in conversation history with corresponding pronominal references in generated questions, which makes generated questions interconnected to conversation history.

Question Answering Question Generation +2

Topic-Aware Neural Keyphrase Generation for Social Media Language

2 code implementations ACL 2019 Yue Wang, Jing Li, Hou Pong Chan, Irwin King, Michael R. Lyu, Shuming Shi

Further discussions show that our model learns meaningful topics, which interprets its superiority in social media keyphrase generation.

Keyphrase Generation

Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards

1 code implementation ACL 2019 Hou Pong Chan, Wang Chen, Lu Wang, Irwin King

To address this problem, we propose a reinforcement learning (RL) approach for keyphrase generation, with an adaptive reward function that encourages a model to generate both sufficient and accurate keyphrases.

Keyphrase Generation reinforcement-learning +1

STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems

no code implementations27 May 2019 Jiani Zhang, Xingjian Shi, Shenglin Zhao, Irwin King

We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario.

Link Prediction Matrix Completion +1

Doctor of Crosswise: Reducing Over-parametrization in Neural Networks

1 code implementation24 May 2019 J. D. Curtó, I. C. Zarza, Kris Kitani, Irwin King, Michael R. Lyu

Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks.

Microblog Hashtag Generation via Encoding Conversation Contexts

1 code implementation NAACL 2019 Yue Wang, Jing Li, Irwin King, Michael R. Lyu, Shuming Shi

Automatic hashtag annotation plays an important role in content understanding for microblog posts.

Topic Models

HiGRU: Hierarchical Gated Recurrent Units for Utterance-level Emotion Recognition

1 code implementation NAACL 2019 Wenxiang Jiao, Haiqin Yang, Irwin King, Michael R. Lyu

In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3) long-range contextual information is hard to be effectively captured.

Emotion Recognition

An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction

1 code implementation NAACL 2019 Wang Chen, Hou Pong Chan, Piji Li, Lidong Bing, Irwin King

For further exploiting the power of extraction and retrieval, we propose a neural-based merging module to combine and re-rank the predicted keyphrases from the enhanced generative model, the extractive model, and the retrieved keyphrases.

Keyphrase Generation Multi-Task Learning +1

DDFlow: Learning Optical Flow with Unlabeled Data Distillation

1 code implementation25 Feb 2019 Pengpeng Liu, Irwin King, Michael R. Lyu, Jia Xu

We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data.

Optical Flow Estimation

Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs

no code implementations NeurIPS 2018 Han Shao, Xiaotian Yu, Irwin King, Michael R. Lyu

In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite moments of order $1+\epsilon$, for some $\epsilon\in (0, 1]$.

Thread Popularity Prediction and Tracking with a Permutation-invariant Model

no code implementations EMNLP 2018 Hou Pong Chan, Irwin King

This task has been formulated as a reinforcement learning problem, in which the reward of the agent is the sum of positive responses received by the recommended comments.

Generating Distractors for Reading Comprehension Questions from Real Examinations

2 code implementations8 Sep 2018 Yifan Gao, Lidong Bing, Piji Li, Irwin King, Michael R. Lyu

We investigate the task of distractor generation for multiple choice reading comprehension questions from examinations.

Distractor Generation Multiple-choice +2

Title-Guided Encoding for Keyphrase Generation

no code implementations26 Aug 2018 Wang Chen, Yifan Gao, Jiani Zhang, Irwin King, Michael R. Lyu

Keyphrase generation (KG) aims to generate a set of keyphrases given a document, which is a fundamental task in natural language processing (NLP).

Keyphrase Generation

Difficulty Controllable Generation of Reading Comprehension Questions

no code implementations10 Jul 2018 Yifan Gao, Lidong Bing, Wang Chen, Michael R. Lyu, Irwin King

We investigate the difficulty levels of questions in reading comprehension datasets such as SQuAD, and propose a new question generation setting, named Difficulty-controllable Question Generation (DQG).

Question Generation Question-Generation +2

DeepObfuscation: Securing the Structure of Convolutional Neural Networks via Knowledge Distillation

no code implementations27 Jun 2018 Hui Xu, Yuxin Su, Zirui Zhao, Yangfan Zhou, Michael R. Lyu, Irwin King

Our obfuscation approach is very effective to protect the critical structure of a deep learning model from being exposed to attackers.

Cryptography and Security

Code Completion with Neural Attention and Pointer Networks

1 code implementation27 Nov 2017 Jian Li, Yue Wang, Michael R. Lyu, Irwin King

Intelligent code completion has become an essential research task to accelerate modern software development.

Code Completion

Semantically Consistent Image Completion with Fine-grained Details

no code implementations26 Nov 2017 Pengpeng Liu, Xiaojuan Qi, Pinjia He, Yikang Li, Michael R. Lyu, Irwin King

Image completion has achieved significant progress due to advances in generative adversarial networks (GANs).

Image Inpainting

High-Resolution Deep Convolutional Generative Adversarial Networks

1 code implementation17 Nov 2017 Joachim D. Curtó, Irene C. Zarza, Fernando de la Torre, Irwin King, Michael R. Lyu

Generative Adversarial Networks (GANs) convergence in a high-resolution setting with a computational constrain of GPU memory capacity (from 12GB to 24 GB) has been beset with difficulty due to the known lack of convergence rate stability.

 Ranked #1 on Image Generation on CelebA 128x128 (MS-SSIM metric)

Image Generation MS-SSIM +2

Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network

no code implementations CIKM 2017 Jiajun Cheng, Shenglin Zhao, Jiani Zhang, Irwin King, Xin Zhang, Hui Wang

However, the prior work only attends to the sentiment information and ignores the aspect-related information in the text, which may cause mismatching between the sentiment words and the aspects when an unrelated sentiment word is semantically meaningful for the given aspect.

Classification Sentence +2

Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data

no code implementations ICML 2017 Xixian Chen, Michael R. Lyu, Irwin King

Estimating covariance matrices is a fundamental technique in various domains, most notably in machine learning and signal processing.

Data Compression

Learning to Rank Using Localized Geometric Mean Metrics

1 code implementation22 May 2017 Yuxin Su, Irwin King, Michael Lyu

First, we design a concept called \textit{ideal candidate document} to introduce metric learning algorithm to query-independent model.

Computational Efficiency Learning-To-Rank +1

Dynamic Key-Value Memory Networks for Knowledge Tracing

1 code implementation24 Nov 2016 Jiani Zhang, Xingjian Shi, Irwin King, Dit-yan Yeung

Knowledge Tracing (KT) is a task of tracing evolving knowledge state of students with respect to one or more concepts as they engage in a sequence of learning activities.

Knowledge Tracing

Simple and Efficient Parallelization for Probabilistic Temporal Tensor Factorization

no code implementations11 Nov 2016 Guangxi Li, Zenglin Xu, Linnan Wang, Jinmian Ye, Irwin King, Michael Lyu

Probabilistic Temporal Tensor Factorization (PTTF) is an effective algorithm to model the temporal tensor data.

A Survey of Point-of-interest Recommendation in Location-based Social Networks

no code implementations3 Jul 2016 Shenglin Zhao, Irwin King, Michael R. Lyu

Then, we present a comprehensive review in three aspects: influential factors for POI recommendation, methodologies employed for POI recommendation, and different tasks in POI recommendation.

Movie Recommendation Recommendation Systems

Heavy-Tailed Symmetric Stochastic Neighbor Embedding

no code implementations NeurIPS 2009 Zhirong Yang, Irwin King, Zenglin Xu, Erkki Oja

Based on this finding, we present a parameterized subset of similarity functions for choosing the best tail-heaviness for HSSNE; (2) we present a fixed-point optimization algorithm that can be applied to all heavy-tailed functions and does not require the user to set any parameters; and (3) we present two empirical studies, one for unsupervised visualization showing that our optimization algorithm runs as fast and as good as the best known t-SNE implementation and the other for semi-supervised visualization showing quantitative superiority using the homogeneity measure as well as qualitative advantage in cluster separation over t-SNE.

Data Visualization

Adaptive Regularization for Transductive Support Vector Machine

no code implementations NeurIPS 2009 Zenglin Xu, Rong Jin, Jianke Zhu, Irwin King, Michael Lyu, Zhirong Yang

In this framework, SVM and TSVM can be regarded as a learning machine without regularization and one with full regularization from the unlabeled data, respectively.

An Extended Level Method for Efficient Multiple Kernel Learning

no code implementations NeurIPS 2008 Zenglin Xu, Rong Jin, Irwin King, Michael Lyu

We consider the problem of multiple kernel learning (MKL), which can be formulated as a convex-concave problem.

Learning with Consistency between Inductive Functions and Kernels

no code implementations NeurIPS 2008 Haixuan Yang, Irwin King, Michael Lyu

Regularized Least Squares (RLS) algorithms have the ability to avoid over-fitting problems and to express solutions as kernel expansions.

Efficient Convex Relaxation for Transductive Support Vector Machine

no code implementations NeurIPS 2007 Zenglin Xu, Rong Jin, Jianke Zhu, Irwin King, Michael Lyu

We consider the problem of Support Vector Machine transduction, which involves a combinatorial problem with exponential computational complexity in the number of unlabeled examples.

Cannot find the paper you are looking for? You can Submit a new open access paper.