7 papers
Domain-Skewed Federated Learning with Feature Decoupling and Calibration
Huan Wang, Jun Shen, Jun Yan +1
Federated learning (FL) allows distributed clients to collaboratively train a global model in a privacy-preserving manner. However, one major challenge is domain skew, where client…
Identifying Good and Bad Neurons for Task-Level Controllable LLMs
Wenjie Li, Guansong Pang, Hezhe Qiao +2
Large Language Models have demonstrated remarkable capabilities on multiple-choice question answering benchmarks, but the complex mechanisms underlying their large-scale neurons re…
Semi-supervised Graph Anomaly Detection via Robust Homophily Learning
Guoguo Ai, Hezhe Qiao, Hui Yan +1
Semi-supervised graph anomaly detection (GAD) utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. Current method…
AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection
Hezhe Qiao, Chaoxi Niu, Ling Chen +1
Graph anomaly detection (GAD) aims to identify abnormal nodes that differ from the majority of the nodes in a graph, which has been attracting significant attention in recent years…
GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
Guoguo Ai, Guansong Pang, Hezhe Qiao +2
Graph Transformers (GTs) have demonstrated remarkable performance in graph representation learning over popular graph neural networks (GNNs). However, self--attention, the core mod…
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
Chaoxi Niu, Guansong Pang, Ling Chen +1
Class-incremental learning (CIL) aims to continually learn a sequence of tasks, with each task consisting of a set of unique classes. Graph CIL (GCIL) follows the same setting but…