A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions
For researchers in graph representation learning, this work provides a more flexible and effective multi-level contrastive learning approach that eliminates hyperparameter tuning overhead.
This paper proposes a unified contrastive framework for graph self-supervised learning that integrates node-level, proximity-level, cluster-level, and graph-level representations via a linear combination of similarity and dissimilarity scores, and introduces a parameter-free self-weighting mechanism to adaptively assign weights to individual scores. The method consistently outperforms state-of-the-art approaches on classification, clustering, and link prediction tasks across real-world datasets.
Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing methods still predominantly focus on a single graph abstraction level. To address this limitation, we propose a unified contrastive framework that can target node-level, proximity-level, cluster-level, and graph-level information and integrate them through a linear combination of similarity scores on positive pairs and dissimilarity scores (i.e., similarity scores on negative pairs). Furthermore, current approaches typically assign uniform penalty strengths to all examples, which reduces optimization flexibility and leads to ambiguous convergence status. To overcome this, we introduce a novel parameter-free fine-grained self-weighting mechanism that adaptively assigns weights to individual similarity and dissimilarity scores. The proposed mechanism emphasizes the scores that deviate significantly from their target values. Our approach not only enhances optimization flexibility but also eliminates the computational overhead of hyperparameter tuning in conventional multi-task GSSL methods. Comprehensive experiments on real-world datasets show that our methods consistently outperform state-of-the-art approaches across downstream tasks, including classification, clustering, and link prediction, in both single-level and multi-level scenarios.