6 citations · 8 across the 19 of their papers we have counts for
21 papers
Self-Gating Attention for Efficient Time Series Forecasting
Dezheng Wang, Tong Chen, Wei Yuan +3
Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical…
FOSTER: First-order Dataset Distillation for Text-based Sequential Recommendation
Hung Vinh Tran, Tong Chen, Xinyi Gao +3
Text-based sequential recommender systems, while greatly improving recommendation accuracy by incorporating item contexts, are undeniably more expensive to train. By condensing a l…
GRAFT: Graph-Tokenized LLMs for Tool Planning
Xinyi Gao, Xinyu Ren, Junliang Yu +3
Large language models (LLMs) are increasingly used to complete complex tasks by selecting and coordinating external tools across multiple steps. This requires aligning tool choices…
Prompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems
Yuchuan Zhao, Tong Chen, Junliang Yu +3
Large language model-powered sequential recommender systems (LLM-SRSs) have recently demonstrated remarkable performance, enabling recommendations through prompt-driven inference o…
Evolutionary Router Feature Generation for Zero-Shot Graph Anomaly Detection with Mixture-of-Experts
Haiyang Jiang, Tong Chen, Xinyi Gao +3
Zero-shot graph anomaly detection (GAD) has attracted increasing attention recent years, yet the heterogeneity of graph structures, features, and anomaly patterns across graphs mak…
LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detection
Dezheng Wang, Tong Chen, Guansong Pang +3
As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of…
When Text-as-Vision Meets Semantic IDs in Generative Recommendation: An Empirical Study
Shutong Qiao, Wei Yuan, Tong Chen +3
Semantic ID learning is a key interface in Generative Recommendation (GR) models, mapping items to discrete identifiers grounded in side information, most commonly via a pretrained…
ProEx: A Unified Framework Leveraging Large Language Model with Profile Extrapolation for Recommendation
Yi Zhang, Yiwen Zhang, Yu Wang +2
The powerful text understanding and generation capabilities of large language models (LLMs) have brought new vitality to general recommendation with implicit feedback. One possible…
Relational Database Distillation: From Structured Tables to Condensed Graph Data
Xinyi Gao, Jingxi Zhang, Lijian Chen +3
Relational databases (RDBs) underpin the majority of global data management systems, where information is structured into multiple interdependent tables. To effectively use the kno…
Towards Distribution Matching between Collaborative and Language Spaces for Generative Recommendation
Yi Zhang, Yiwen Zhang, Yu Wang +2
Generative recommendation aims to learn the underlying generative process over the entire item set to produce recommendations for users. Although it leverages non-linear probabilis…
Progressive Generalization Risk Reduction for Data-Efficient Causal Effect Estimation
Hechuan Wen, Tong Chen, Guanhua Ye +3
Causal effect estimation (CEE) provides a crucial tool for predicting the unobserved counterfactual outcome for an entity. As CEE relaxes the requirement for ``perfect'' counterfac…
Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning
Xinyi Gao, Yayong Li, Tong Chen +3
With the increasing computation of training graph neural networks (GNNs) on large-scale graphs, graph condensation (GC) has emerged as a promising solution to synthesize a compact,…
Epidemiology-informed Network for Robust Rumor Detection
Wei Jiang, Tong Chen, Xinyi Gao +3
The rapid spread of rumors on social media has posed significant challenges to maintaining public trust and information integrity. Since an information cascade process is essential…
FELLAS: Enhancing Federated Sequential Recommendation with LLM as External Services
Wei Yuan, Chaoqun Yang, Guanhua Ye +3
Federated sequential recommendation (FedSeqRec) has gained growing attention due to its ability to protect user privacy. Unfortunately, the performance of FedSeqRec is still unsati…
Physics-guided Active Sample Reweighting for Urban Flow Prediction
Wei Jiang, Tong Chen, Guanhua Ye +4
Urban flow prediction is a spatio-temporal modeling task that estimates the throughput of transportation services like buses, taxis, and ride-sharing, where data-driven models have…
Graph Condensation for Open-World Graph Learning
Xinyi Gao, Tong Chen, Wentao Zhang +3
The burgeoning volume of graph data presents significant computational challenges in training graph neural networks (GNNs), critically impeding their efficiency in various applicat…
RobGC: Towards Robust Graph Condensation
Xinyi Gao, Hongzhi Yin, Tong Chen +3
Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale…
Diffusion-Based Cloud-Edge-Device Collaborative Learning for Next POI Recommendations
Jing Long, Guanhua Ye, Tong Chen +3
The rapid expansion of Location-Based Social Networks (LBSNs) has highlighted the importance of effective next Point-of-Interest (POI) recommendations, which leverage historical ch…
Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition
Xinyi Gao, Guanhua Ye, Tong Chen +3
The increasing prevalence of large-scale graphs poses a significant challenge for graph neural network training, attributed to their substantial computational requirements. In resp…
Challenging Low Homophily in Social Recommendation
Wei Jiang, Xinyi Gao, Guandong Xu +2
Social relations are leveraged to tackle the sparsity issue of user-item interaction data in recommendation under the assumption of social homophily. However, social recommendation…
Graph Condensation: A Survey
Xinyi Gao, Junliang Yu, Tong Chen +3
The rapid growth of graph data poses significant challenges in storage, transmission, and particularly the training of graph neural networks (GNNs). To address these challenges, gr…