Search Results for author:
Found 80 papers, 48 papers with code
ICST-DNET: An Interpretable Causal Spatio-Temporal Diffusion Network for Traffic Speed Prediction
However, making accurate predictions is challenging due to three factors: 1) traffic diffusion, i. e., the spatial and temporal causality existing between the traffic conditions of multiple neighboring roads, 2) the poor interpretability of traffic data with complicated spatio-temporal correlations, and 3) the latent pattern of traffic speed fluctuations over time, such as morning and evening rush.
Graph Continual Learning with Debiased Lossless Memory Replay
Graph continual learning (GCL) tackles this problem by continually adapting GNNs to the expanded graph of the current task while maintaining the performance over the graph of previous tasks.
DSGNN: A Dual-View Supergrid-Aware Graph Neural Network for Regional Air Quality Estimation
To this end, we propose a Dual-view Supergrid-aware Graph Neural Network (DSGNN) for regional air quality estimation, which can model the spatial dependencies of distant grid regions from dual views (i. e., satellite-derived aerosol optical depth (AOD) and meteorology).
D-PAD: Deep-Shallow Multi-Frequency Patterns Disentangling for Time Series Forecasting
A decomposition-reconstruction-decomposition (D-R-D) module is proposed to progressively extract the information of frequencies mixed in the components, corresponding to the "deep" aspect.
Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
We instantiate the path on structured environments and provide feedback to edit the path if anything goes wrong.
Large Language Multimodal Models for 5-Year Chronic Disease Cohort Prediction Using EHR Data
In our experiments, we observe that clinicalBERT and PubMed-BERT, when combined with attention fusion, can achieve an accuracy of 73% in multiclass chronic diseases and diabetes prediction.
RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering
Based on our findings, we propose Time-Aware Adaptive Retrieval (TA-ARE), a simple yet effective method that helps LLMs assess the necessity of retrieval without calibration or additional training.
Rethinking Human-like Translation Strategy: Integrating Drift-Diffusion Model with Large Language Models for Machine Translation
Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation.
SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models
In the next stage, we train the skill router using task-specific downstream data and use this router to integrate the acquired skills with LLMs during inference.
Continuously Evolving Graph Neural Controlled Differential Equations for Traffic Forecasting
In this paper, we propose Continuously Evolving Graph Neural Controlled Differential Equations (CEGNCDE) to capture continuous temporal dependencies and spatial dependencies over time simultaneously.
Large Language Models Are Neurosymbolic Reasoners
A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning.
MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting
In addition, a tri-stage message passing mechanism is introduced to aggregate pattern information and learn the interaction strength between temporal patterns of different scales.
Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game
This problem motivates the area of ad hoc teamwork, in which an agent may potentially cooperate with a variety of teammates to achieve a shared goal.
Brain Diffuser with Hierarchical Transformer for MCI Causality Analysis
It can captures both unidirectal and bidirectional interactions between brain regions, providing a comprehensive understanding of the brain's information processing mechanisms.
TPRNN: A Top-Down Pyramidal Recurrent Neural Network for Time Series Forecasting
Then by executing a multi-scale information interaction module from top to bottom, we model both the temporal dependencies of each scale and the influences of subsequences of different scales, resulting in a complete modeling of multi-scale temporal patterns in time series.
Enhancing Low-dose CT Image Reconstruction by Integrating Supervised and Unsupervised Learning
In our experiments, we study combinations of supervised deep network reconstructors and MBIR solver with learned sparse representation-based priors or analytical priors.
Turn-Level Active Learning for Dialogue State Tracking
Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems.
CITB: A Benchmark for Continual Instruction Tuning
In this work, we establish a CIT benchmark consisting of learning and evaluation protocols.
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances
Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment.
WeatherGNN: Exploiting Complicated Relationships in Numerical Weather Prediction Bias Correction
In addition, the interactions between weather factors are further complicated by the spatial dependencies between regions, which are influenced by varied terrain and atmospheric motions.
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
Reconstructing 3D clothed human avatars from single images is a challenging task, especially when encountering complex poses and loose clothing.
ABS-SGD: A Delayed Synchronous Stochastic Gradient Descent Algorithm with Adaptive Batch Size for Heterogeneous GPU Clusters
In this paper, we propose a delayed synchronous SGD algorithm with adaptive batch size (ABS-SGD) for heterogeneous GPU clusters.
HRGCN: Heterogeneous Graph-level Anomaly Detection with Hierarchical Relation-augmented Graph Neural Networks
To address the problem, we propose HRGCN, an unsupervised deep heterogeneous graph neural network, to model complex heterogeneous relations between different entities in the system for effectively identifying these anomalous behaviour graphs.
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models.
Ranked #56 on
Visual Question Answering
on MM-Vet
CSCLog: A Component Subsequence Correlation-Aware Log Anomaly Detection Method
To this end, we propose CSCLog, a Component Subsequence Correlation-Aware Log anomaly detection method, which not only captures the sequential dependencies in subsequences, but also models the implicit correlations of subsequences.
Graph-level Anomaly Detection via Hierarchical Memory Networks
One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole.
DSTCGCN: Learning Dynamic Spatial-Temporal Cross Dependencies for Traffic Forecasting
Traffic forecasting is essential to intelligent transportation systems, which is challenging due to the complicated spatial and temporal dependencies within a road network.
Semi-supervised Credit Card Fraud Detection via Attribute-driven Graph Representation
Then we pass messages among the nodes through a Gated Temporal Attention Network (GTAN) to learn the transaction representation.
Ranked #1 on
Node Classification
on Amazon-Fraud
CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models
We evaluate two popular pretrained Chinese conversational models, CDial-GPT and EVA2. 0, using CHBias.
Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
In MOTOR, we combine two kinds of basic medical knowledge, i. e., general and specific knowledge, in a complementary manner to boost the general pretraining process.
Disentangled Pre-training for Image Matting
The pre-training task is designed in a similar manner as image matting, where random trimap and alpha matte are generated to achieve an image disentanglement objective.
SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data.
GTRL: An Entity Group-Aware Temporal Knowledge Graph Representation Learning Method
GTRL is the first work that incorporates the entity group modeling to capture the correlation between entities by stacking only a finite number of layers.
Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning
To tackle this problem, this article proposes a novel approach that builds a discriminative model on collective affinity information (i. e., two sets of pairwise affinities between the negative instances and the anchor instance) to mine hard negatives in GCL.
Hospital transfer risk prediction for COVID-19 patients from a medicalized hotel based on Diffusion GraphSAGE
The proposed models achieved AUC scores above 0. 83 for hospital transfer risk prediction based on the measurements of past 1, 2, and 3 days, outperforming baseline machine learning methods.
Mask Matching Transformer for Few-Shot Segmentation
Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level to obtain segmentation results.
SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition
SWL-Adapt calculates sample weights according to the classification loss and domain discrimination loss of each sample with a parameterized network.
Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting
On the one hand, our model simultaneously incorporates spatial (node-wise) embeddings and temporal (time-wise) embeddings to account for heterogeneous space-and-time convolutions; on the other hand, it uses GAN structure to systematically evaluate statistical consistencies between the real and the predicted time series in terms of both the temporal trending and the complex spatial-temporal dependencies.
CLMFormer: Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System
To further enhance forecasting accuracy, we introduce a memory-driven decoder.
Diminishing Empirical Risk Minimization for Unsupervised Anomaly Detection
Empirically, DERM outperformed the state-of-the-art on the unsupervised AD benchmark consisting of 18 datasets.
Combining Deep Learning and Adaptive Sparse Modeling for Low-dose CT Reconstruction
Recent application of deep learning methods for image reconstruction provides a successful data-driven approach to addressing the challenges when reconstructing images with measurement undersampling or various types of noise.
Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics
Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics.
Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
Text-based games provide an interactive way to study natural language processing.
Fine-Grained Population Mobility Data-Based Community-Level COVID-19 Prediction Model
Predicting the number of infections in the anti-epidemic process is extremely beneficial to the government in developing anti-epidemic strategies, especially in fine-grained geographic units.
Informative Pseudo-Labeling for Graph Neural Networks with Few Labels
It aims to augment the training set with pseudo-labeled unlabeled nodes with high confidence so as to re-train a supervised model in a self-training cycle.
Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting
Given the multi-scale feature representations and scale-specific inter-variable dependencies, a multi-scale temporal graph neural network is introduced to jointly model intra-variable dependencies and inter-variable dependencies.
Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs.
Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting
In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF).
Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting
Time series forecasting is a significant problem in many applications, e. g., financial predictions and business optimization.
RMNA: A Neighbor Aggregation-Based Knowledge Graph Representation Learning Model Using Rule Mining
Therefore, neighbor aggregation-based representation learning (NARL) models are proposed, which encode the information in the neighbors of an entity into its embeddings.
TME-BNA: Temporal Motif-Preserving Network Embedding with Bicomponent Neighbor Aggregation
Evolving temporal networks serve as the abstractions of many real-life dynamic systems, e. g., social network and e-commerce.
Multi-Relation Aware Temporal Interaction Network Embedding
However, existing temporal interaction network embedding methods only use historical interaction relations to mine neighbor nodes, ignoring other relation types.
Goal Randomization for Playing Text-based Games without a Reward Function
In a variety of text-based games, we show that this simple method results in competitive performance for agents.
Generalization in Text-based Games via Hierarchical Reinforcement Learning
Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Multi-Level Visual Similarity Based Personalized Tourist Attraction Recommendation Using Geo-Tagged Photos
In addition, to capture the significances of different photos, we exploit the self-attention mechanism to obtain the visual representations of users and tourist attractions.
Group-Aware Graph Neural Network for Nationwide City Air Quality Forecasting
The model constructs a city graph and a city group graph to model the spatial and latent dependencies between cities, respectively.
SALIENCE: An Unsupervised User Adaptation Model for Multiple Wearable Sensors Based Human Activity Recognition
In order to address the challenge that the transferabilities of different sensors are different, we propose SALIENCE (unsupervised user adaptation model for multiple wearable sensors based human activity recognition) model.
DexDeepFM: Ensemble Diversity Enhanced Extreme Deep Factorization Machine Model
In this paper, an ensemble diversity enhanced extreme deep factorization machine model (DexDeepFM) is proposed, which designs the ensemble diversity measure in each hidden layer and considers both ensemble diversity and prediction accuracy in the objective function.
Homophily Outlier Detection in Non-IID Categorical Data
Most of existing outlier detection methods assume that the outlier factors (i. e., outlierness scoring measures) of data entities (e. g., feature values and data objects) are Independent and Identically Distributed (IID).
Unified Robust Training for Graph NeuralNetworks against Label Noise
Learning with label noise has been primarily studied in the context of image classification, but these techniques cannot be directly applied to graph-structured data, due to two major challenges -- label sparsity and label dependency -- faced by learning on graphs.
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally.
HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method
Existing air quality forecasting methods cannot effectively model the diffusion processes of air pollutants between cities and monitoring stations, which may suddenly deteriorate the air quality of a region.
A Multi-Mode Modulator for Multi-Domain Few-Shot Classification
Most existing few-shot classification methods only consider generalization on one dataset (i. e., single-domain), failing to transfer across various seen and unseen domains.
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language.
Histopathology of Third Trimester Placenta from SARS-CoV-2-Positive Women
Results: Twenty-one 3rd-trimester, placentas from SARS-CoV-2-positive women were identified and compared to 20 placentas from SARS-CoV-2-negative women.
Smoothing Graphons for Modelling Exchangeable Relational Data
We initially propose the Integrated Smoothing Graphon (ISG) which introduces one smoothing parameter to the SBM graphon to generate continuous relational intensity values.
Recurrent Dirichlet Belief Networks for Interpretable Dynamic Relational Data Modelling
In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable hidden structures from dynamic relational data.
Relational State-Space Model for Stochastic Multi-Object Systems
Real-world dynamical systems often consist of multiple stochastic subsystems that interact with each other.
Scalable Deep Generative Relational Model with High-Order Node Dependence
In this work, we propose a probabilistic framework for relational data modelling and latent structure exploring.
Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
Traffic forecasting is of great importance to transportation management and public safety, and very challenging due to the complicated spatial-temporal dependency and essential uncertainty brought about by the road network and traffic conditions.
Scalable Deep Generative Relational Models with High-Order Node Dependence
We propose a probabilistic framework for modelling and exploring the latent structure of relational data.
SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphs
In this paper, we propose a SEmi-supervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy in an adversarial way.
A Review for Weighted MinHash Algorithms
In this review, we mainly categorize the Weighted MinHash algorithms into quantization-based approaches, "active index"-based ones and others, and show the evolution and inherent connection of the weighted MinHash algorithms, from the integer weighted MinHash algorithms to real-valued weighted MinHash ones (particularly the Consistent Weighted Sampling scheme).
Data Structures and Algorithms
Binarized Attributed Network Embedding
To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation.
Ranked #1 on
Link Prediction
on Wiki
Privacy-preserving Stochastic Gradual Learning
PRESTIGE bridges private updates of the primal variable (by private sampling) with the gradual curriculum learning (CL).
Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection
However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i. e., outliers).
Improved Consistent Weighted Sampling Revisited
Min-Hash is a popular technique for efficiently estimating the Jaccard similarity of binary sets.
Data Structures and Algorithms
Personalized Video Recommendation Using Rich Contents from Videos
In the existing video recommender systems, the models make the recommendations based on the user-video interactions and single specific content features.
Extracting Actionability from Machine Learning Models by Sub-optimal Deterministic Planning
Our work represents a new application of automated planning on an emerging and challenging machine learning paradigm.
On the Convergence of A Family of Robust Losses for Stochastic Gradient Descent
The convergence of Stochastic Gradient Descent (SGD) using convex loss functions has been widely studied.
