Hypergraph Self-supervised Learning with Sampling-efficient Signals
This work addresses hypergraph representation learning for domains requiring efficient SSL without labels, but it is incremental as it builds on existing hypergraph SSL methods.
The paper tackled the problem of self-supervised learning on hypergraphs by addressing limitations in existing contrastive methods, such as unreliable negative sampling and high computational costs, and proposed SE-HSSL with sampling-efficient signals, achieving superior effectiveness and efficiency over state-of-the-art methods on 7 real-world hypergraphs.
Self-supervised learning (SSL) provides a promising alternative for representation learning on hypergraphs without costly labels. However, existing hypergraph SSL models are mostly based on contrastive methods with the instance-level discrimination strategy, suffering from two significant limitations: (1) They select negative samples arbitrarily, which is unreliable in deciding similar and dissimilar pairs, causing training bias. (2) They often require a large number of negative samples, resulting in expensive computational costs. To address the above issues, we propose SE-HSSL, a hypergraph SSL framework with three sampling-efficient self-supervised signals. Specifically, we introduce two sampling-free objectives leveraging the canonical correlation analysis as the node-level and group-level self-supervised signals. Additionally, we develop a novel hierarchical membership-level contrast objective motivated by the cascading overlap relationship in hypergraphs, which can further reduce membership sampling bias and improve the efficiency of sample utilization. Through comprehensive experiments on 7 real-world hypergraphs, we demonstrate the superiority of our approach over the state-of-the-art method in terms of both effectiveness and efficiency.