Search Results for author:
Found 61 papers, 36 papers with code
A Closer Look at Few-Shot Out-of-Distribution Intent Detection
Comprehensive experiments on three real-world intent detection benchmark datasets demonstrate the high effectiveness of our proposed approach and its great potential in improving state-of-the-art methods for few-shot OOD intent detection.
VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection
Out-of-distribution (OOD) detection plays a crucial role in ensuring the safety and reliability of deep neural networks in various applications.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+4
Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey
The recent advancements in pretrained multimodal models offer new opportunities and challenges in developing content-aware recommender systems.
Decoy Effect In Search Interaction: Understanding User Behavior and Measuring System Vulnerability
This study examines the decoy effect's underexplored influence on user search interactions and methods for measuring information retrieval (IR) systems' vulnerability to this effect.
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
Universal image restoration is a practical and potential computer vision task for real-world applications.
Discrete Semantic Tokenization for Deep CTR Prediction
Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios.
Benchmarking News Recommendation in the Era of Green AI
Over recent years, news recommender systems have gained significant attention in both academia and industry, emphasizing the need for a standardized benchmark to evaluate and compare the performance of these systems.
Decoy Effect in Search Interaction: A Pilot Study
In recent years, the influence of cognitive effects and biases on users' thinking, behaving, and decision-making has garnered increasing attention in the field of interactive information retrieval.
Towards LLM-driven Dialogue State Tracking
In this study, we conduct an initial examination of ChatGPT's capabilities in DST.
TF-DCon: Leveraging Large Language Models (LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation
Notably, the condensation paradigm of this method is forward and free from iterative optimization on the synthesized dataset.
EasyGen: Easing Multimodal Generation with a Bidirectional Conditional Diffusion Model and LLMs
We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs).
SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
In particular, we cluster the extensive degradation space to create a set of representative degradation cases, which serves as a comprehensive test set.
Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector Quantization
Category information plays a crucial role in enhancing the quality and personalization of recommender systems.
DiffuVolume: Diffusion Model for Volume based Stereo Matching
Our method, termed DiffuVolume, considers the diffusion model as a cost volume filter, which will recurrently remove the redundant information from the cost volume.
Only Encode Once: Making Content-based News Recommender Greener
Large pretrained language models (PLM) have become de facto news encoders in modern news recommender systems, due to their strong ability in comprehending textual content.
How Good Are LLMs at Out-of-Distribution Detection?
Out-of-distribution (OOD) detection plays a vital role in enhancing the reliability of machine learning (ML) models.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training
The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem.
Neighborhood-based Hard Negative Mining for Sequential Recommendation
Motivated by this observation, we propose a Graph-based Negative sampling approach based on Neighborhood Overlap (GNNO) to exploit structural information hidden in user behaviors for negative mining.
Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark
With the availability of large-scale, comprehensive, and general-purpose vision-language (VL) datasets such as MSCOCO, vision-language pre-training (VLP) has become an active area of research and proven to be effective for various VL tasks such as visual-question answering.
Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training
We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount of labeled data.
ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
Personalized content-based recommender systems have become indispensable tools for users to navigate through the vast amount of content available on platforms like daily news websites and book recommendation services.
Continual Graph Convolutional Network for Text Classification
Graph convolutional network (GCN) has been successfully applied to capture global non-consecutive and long-distance semantic information for text classification.
FANS: Fast Non-Autoregressive Sequence Generation for Item List Continuation
Item list continuation is proposed to model the overall trend of a list and predict subsequent items.
Boosting Few-Shot Text Classification via Distribution Estimation
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain.
Few-Shot Image Classification
Few-Shot Text Classification
+1
SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency
For this purpose, we develop a prompt based on the features of depth differences between the hazy input images and corresponding clear counterparts that can guide dehazing models for better restoration.
Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning
Our experiments show that such a simple approach can greatly reduce the occurrence of conflicting gradients in the remaining shared layers and achieve better performance, with only a slight increase in model parameters in many cases.
Simple yet Effective Gradient-Free Graph Convolutional Networks
Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning.
Generating Anomalies for Video Anomaly Detection With Prompt-Based Feature Mapping
There also exists a scene gap between virtual and real scenarios, including scene-specific anomalies (events that are abnormal in one scene but normal in another) and scene-specific attributes, such as the viewpoint of the surveillance camera.
Anomaly Detection In Surveillance Videos
Video Anomaly Detection
Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement
The generator is based on a U-shaped Transformer which is used to explore non-local information for better clear image restoration.
Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning
Accordingly, we first exclude these surely non-existent categories by a complementary learning loss.
New Intent Discovery with Pre-training and Contrastive Learning
Existing approaches typically rely on a large amount of labeled utterances and employ pseudo-labeling methods for representation learning and clustering, which are label-intensive, inefficient, and inaccurate.
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization
It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations.
A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds
The recently proposed practical degradation model includes a full spectrum of degradation types, but only considers complex cases that use all degradation types in the degradation process, while ignoring many important corner cases that are common in the real world.
Online-updated High-order Collaborative Networks for Single Image Deraining
Most of the existing deep-learning-based methods constrain the network to generate derained images but few of them explore features from intermediate layers, different levels, and different modules which are beneficial for rain streaks removal.
Modeling User Behavior with Graph Convolution for Personalized Product Search
Our approach can be seamlessly integrated with existing latent space based methods and be potentially applied in any product retrieval method that uses purchase history to model user preferences.
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting.
Ranked #7 on
Few-Shot Class-Incremental Learning
on mini-Imagenet
Effectiveness of Pre-training for Few-shot Intent Classification
This paper investigates the effectiveness of pre-training for few-shot intent classification.
Online Enhanced Semantic Hashing: Towards Effective and Efficient Retrieval for Streaming Multi-Modal Data
With the vigorous development of multimedia equipment and applications, efficient retrieval of large-scale multi-modal data has become a trendy research topic.
Adaptation-Agnostic Meta-Training
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update.
Embedding-based Product Retrieval in Taobao Search
We evaluate MGDSPR on Taobao Product Search with significant metrics gains observed in offline experiments and online A/B tests.
Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Since the distribution of outlier utterances is arbitrary and unknown in the training stage, existing methods commonly rely on strong assumptions on data distribution such as mixture of Gaussians to make inference, resulting in either complex multi-step training procedures or hand-crafted rules such as confidence threshold selection for outlier detection.
SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering
We show that SLAKE can be used to facilitate the development and evaluation of Med-VQA systems.
A Closer Look at the Training Strategy for Modern Meta-Learning
The support/query (S/Q) episodic training strategy has been widely used in modern meta-learning algorithms and is believed to improve their generalization ability to test environments.
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification
User intent classification plays a vital role in dialogue systems.
M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
Most existing methods can be categorized as \emph{multi-view representation fusion}; they first build one graph and then integrate multi-view data into a single compact representation for each node in the graph.
Self-Supervised Graph Representation Learning via Global Context Prediction
To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself.
Variational Metric Scaling for Metric-Based Meta-Learning
In this paper, we recast metric-based meta-learning from a Bayesian perspective and develop a variational metric scaling framework for learning a proper metric scaling parameter.
Reconstructing Capsule Networks for Zero-shot Intent Classification
With the burgeoning of conversational AI, existing systems are not capable of handling numerous fast-emerging intents, which motivates zero-shot intent classification.
Clustering Uncertain Data via Representative Possible Worlds with Consistency Learning
However, there are two issues in existing possible world based algorithms: (1) They rely on all the possible worlds and treat them equally, but some marginal possible worlds may cause negative effects.
Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs
Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that computes the representation of a node by aggregating those of its neighbors.
Attributed Graph Learning with 2-D Graph Convolution
Graph convolutional neural networks have demonstrated promising performance in attributed graph learning, thanks to the use of graph convolution that effectively combines graph structures and node features for learning node representations.
Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution
Existing methods for single network learning cannot solve this problem due to the domain shift across networks.
Attributed Graph Clustering via Adaptive Graph Convolution
Attributed graph clustering is challenging as it requires joint modelling of graph structures and node attributes.
Ranked #3 on
Graph Clustering
on Cora
Label Efficient Semi-Supervised Learning via Graph Filtering
However, existing graph-based methods either are limited in their ability to jointly model graph structures and data features, such as the classical label propagation methods, or require a considerable amount of labeled data for training and validation due to high model complexity, such as the recent neural-network-based methods.
Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
Many interesting problems in machine learning are being revisited with new deep learning tools.
Ranked #3 on
Node Classification
on Facebook
New Insights Into Laplacian Similarity Search
Graph-based computer vision applications rely critically on similarity metrics which compute the pairwise similarity between any pair of vertices on graphs.
Locally Linear Hashing for Extracting Non-Linear Manifolds
Previous efforts in hashing intend to preserve data variance or pairwise affinity, but neither is adequate in capturing the manifold structures hidden in most visual data.
Analyzing the Harmonic Structure in Graph-Based Learning
We show that either explicitly or implicitly, various well-known graph-based models exhibit a common significant \emph{harmonic} structure in its target function -- the value of a vertex is approximately the weighted average of the values of its adjacent neighbors.
Learning with Partially Absorbing Random Walks
We prove that under proper absorption rates, a random walk starting from a set $\mathcal{S}$ of low conductance will be mostly absorbed in $\mathcal{S}$.
Fast Graph Laplacian Regularized Kernel Learning via Semidefinite–Quadratic–Linear Programming
In this paper, we show that a large class of kernel learning problems can be reformulated as semidefinite-quadratic-linear programs (SQLPs), which only contain a simple positive semidefinite constraint, a second-order cone constraint and a number of linear constraints.
