78 citations · 277 across the 32 of their papers we have counts for
32 papers
MIDSim: Simulating Multi-Channel Information Diffusion in Social Media with LLM-Powered Multi-Agent System
Lexi Liu, Qi Cao, Yuanhao Liu +2
Information diffusion in social media shapes public opinion and collective behavior, making its modeling and simulation an important research problem. Existing studies have investi…
Fine-tuning Done Right in Model Editing
Wanli Yang, Rui Tang, Hongyu Zang +6
Fine-tuning, a foundational method for adapting large language models, has long been considered ineffective for model editing. Here, we challenge this belief, arguing that the repo…
The Mirage of Model Editing: Revisiting Evaluation in the Wild
Wanli Yang, Fei Sun, Jiajun Tan +5
Despite near-perfect results reported in the literature, the effectiveness of model editing in real-world applications remains unclear. To bridge this gap, we introduce QAEdit, a n…
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
Kaike Zhang, Qi Cao, Yunfan Wu +3
Adversarial Collaborative Filtering (ACF), which typically applies adversarial perturbations at user and item embeddings through adversarial training, is widely recognized as an ef…
Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
Kaike Zhang, Qi Cao, Yunfan Wu +3
Recommender systems play a pivotal role in mitigating information overload in various fields. Nonetheless, the inherent openness of these systems introduces vulnerabilities, allowi…
Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems
Yunfan Wu, Qi Cao, Shuchang Tao +3
Recent studies have demonstrated the vulnerability of recommender systems to data poisoning attacks, where adversaries inject carefully crafted fake user interactions into the trai…
When to Trust LLMs: Aligning Confidence with Response Quality
Shuchang Tao, Liuyi Yao, Hanxing Ding +6
Despite the success of large language models (LLMs) in natural language generation, much evidence shows that LLMs may produce incorrect or nonsensical text. This limitation highlig…
Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?
Hexiang Tan, Fei Sun, Wanli Yang +3
While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts genera…
Robust Recommender System: A Survey and Future Directions
Kaike Zhang, Qi Cao, Fei Sun +4
With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload. However, their practical…
What makes a successful rebuttal in computer science conferences? : A perspective on social interaction
Junjie Huang, Win-bin Huang, Yi Bu +3
With an exponential increase in submissions to top-tier Computer Science (CS) conferences, more and more conferences have introduced a rebuttal stage to the conference peer review…
Popularity Debiasing from Exposure to Interaction in Collaborative Filtering
Yuanhao Liu, Qi Cao, Huawei Shen +3
Recommender systems often suffer from popularity bias, where popular items are overly recommended while sacrificing unpopular items. Existing researches generally focus on ensuring…
IDEA: Invariant Defense for Graph Adversarial Robustness
Shuchang Tao, Qi Cao, Huawei Shen +3
Despite the success of graph neural networks (GNNs), their vulnerability to adversarial attacks poses tremendous challenges for practical applications. Existing defense methods suf…
Adversarial Learning Data Augmentation for Graph Contrastive Learning in Recommendation
Junjie Huang, Qi Cao, Ruobing Xie +4
Recently, Graph Neural Networks (GNNs) achieve remarkable success in Recommendation. To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-ba…
Graph Adversarial Immunization for Certifiable Robustness
Shuchang Tao, Huawei Shen, Qi Cao +3
Despite achieving great success, graph neural networks (GNNs) are vulnerable to adversarial attacks. Existing defenses focus on developing adversarial training or model modificatio…
Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective
Yige Yuan, Bingbing Xu, Huawei Shen +4
Graph contrastive learning (GCL) emerges as the most representative approach for graph representation learning, which leverages the principle of maximizing mutual information (Info…
Hierarchical Estimation for Effective and Efficient Sampling Graph Neural Network
Yang Li, Bingbing Xu, Qi Cao +2
Improving the scalability of GNNs is critical for large graphs. Existing methods leverage three sampling paradigms including node-wise, layer-wise and subgraph sampling, then desig…
DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph
Kaike Zhang, Qi Cao, Gaolin Fang +4
Unsupervised representation learning for dynamic graphs has attracted a lot of research attention in recent years. Compared with static graph, the dynamic graph is a comprehensive…
Adversarial Camouflage for Node Injection Attack on Graphs
Shuchang Tao, Qi Cao, Huawei Shen +4
Node injection attacks on Graph Neural Networks (GNNs) have received increasing attention recently, due to their ability to degrade GNN performance with high attack success rates.…
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
Liang Hou, Qi Cao, Yige Yuan +7
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation…
Twin Weisfeiler-Lehman: High Expressive GNNs for Graph Classification
Zhaohui Wang, Qi Cao, Huawei Shen +2
The expressive power of message passing GNNs is upper-bounded by Weisfeiler-Lehman (WL) test. To achieve high expressive GNNs beyond WL test, we propose a novel graph isomorphism t…
Single Node Injection Attack against Graph Neural Networks
Shuchang Tao, Qi Cao, Huawei Shen +3
Node injection attack on Graph Neural Networks (GNNs) is an emerging and practical attack scenario that the attacker injects malicious nodes rather than modifying original nodes or…
Signed Bipartite Graph Neural Networks
Junjie Huang, Huawei Shen, Qi Cao +2
Signed networks are such social networks having both positive and negative links. A lot of theories and algorithms have been developed to model such networks (e.g., balance theory)…
PREP: Pre-training with Temporal Elapse Inference for Popularity Prediction
Qi Cao, Huawei Shen, Yuanhao Liu +2
Predicting the popularity of online content is a fundamental problem in various applications. One practical challenge takes roots in the varying length of observation time or predi…
Conditional GANs with Auxiliary Discriminative Classifier
Liang Hou, Qi Cao, Huawei Shen +3
Conditional generative models aim to learn the underlying joint distribution of data and labels to achieve conditional data generation. Among them, the auxiliary classifier generat…