4 papers
Precedence-Constrained Winter Value for Effective Graph Data Valuation
Hongliang Chi, Wei Jin, Charu Aggarwal +1
Data valuation is essential for quantifying data's worth, aiding in assessing data quality and determining fair compensation. While existing data valuation methods have proven effe…
Overcoming Pitfalls in Graph Contrastive Learning Evaluation: Toward Comprehensive Benchmarks
Qian Ma, Hongliang Chi, Hengrui Zhang +6
The rise of self-supervised learning, which operates without the need for labeled data, has garnered significant interest within the graph learning community. This enthusiasm has l…
Active Learning for Graphs with Noisy Structures
Hongliang Chi, Cong Qi, Suhang Wang +1
Graph Neural Networks (GNNs) have seen significant success in tasks such as node classification, largely contingent upon the availability of sufficient labeled nodes. Yet, the exce…
Enhancing Graph Contrastive Learning with Node Similarity
Hongliang Chi, Yao Ma
Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supe…