activity
20202026
most citedAlleviating Structural Distribution Shift in Graph Anomaly Detection

66 citations · 82 across the 6 of their papers we have counts for

collaborators

7 papers

cs.AI2026

Scale over Preference: The Impact of AI-Generated Content on Online Content Ecology

Tianhao Shi, Yang Zhang, Xiaoyan Zhao +8

The rapid proliferation of Artificial Intelligence-Generated Content (AIGC) is fundamentally restructuring online content ecologies, necessitating a rigorous examination of its beh…

cs.LG2024★ 66 cited

Alleviating Structural Distribution Shift in Graph Anomaly Detection

Yuan Gao, Xiang Wang, Xiangnan He +3

Graph anomaly detection (GAD) is a challenging binary classification problem due to its different structural distribution between anomalies and normal nodes -- abnormal nodes are a…

cs.SI2023

MCDAN: a Multi-scale Context-enhanced Dynamic Attention Network for Diffusion Prediction

Xiaowen Wang, Lanjun Wang, Yuting Su +2

Information diffusion prediction aims at predicting the target users in the information diffusion path on social networks. Prior works mainly focus on the observed structure or seq…

cs.CL2023★ 13 cited

NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference

Benfeng Xu, Quan Wang, Zhendong Mao +3

In-Context Learning (ICL), which formulates target tasks as prompt completion conditioned on in-context demonstrations, has become the prevailing utilization of LLMs. In this paper…

cs.LG2022★ 2 cited

Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network

Weijian Chen, Yixin Cao, Fuli Feng +2

Knowledge Graphs (KGs) are becoming increasingly essential infrastructures in many applications while suffering from incompleteness issues. The KG completion task (KGC) automatical…

cs.IR2022★ 1 cited

Addressing Confounding Feature Issue for Causal Recommendation

Xiangnan He, Yang Zhang, Fuli Feng +4

In recommender system, some feature directly affects whether an interaction would happen, making the happened interactions not necessarily indicate user preference. For instance, s…