activity
20242026
collaborators

18 papers

cs.LG2026

Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching

Zhuoyi Peng, Hanlin Gu, Lixin Fan +1

Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media, and e-commerce. Few-shot graph learning on TAGs is hard: with only a handful…

cs.LG2026

GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs

Zhuoyi Peng, Jingzhou Jiang, Hanlin Gu +2

Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and…

cs.CR2026

Quantifying and Defending against the Privacy Risk in Logit-based Federated Learning

Sheng Wan, Dashan Gao, Hanlin Gu +3

Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among clients. Unlike traditional parameter-based FL methods that e…

cs.LG2026

Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity

Junxiang Wu, Zhiqiang Kou, Hongwei Zeng +7

Label Distribution Learning (LDL) models supervision as an instance-wise probability distribution, enabling fine-grained learning under inherent ambiguity, but its success relies o…

cs.LG2026

FedIDM: Achieving Fast and Stable Convergence in Byzantine Federated Learning through Iterative Distribution Matching

He Yang, Dongyi Lv, Wei Xi +3

Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence. Moreover, when handling a substantial proportion of colluded malicious cli…

cs.LG2026

InkDrop: Invisible Backdoor Attacks Against Dataset Condensation

He Yang, Dongyi Lv, Song Ma +4

Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. How…