Metraipolis › archive › dc_a0cd3c96cb53
SAC-GCL: Structure-Aware Compression for Graph Contrastive Learning — arXiv:2610.37898
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.37898
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:21:04.966Z
- SHA-256 of the archived text
30f2371de2c501fdbb68c498e10b46c96bb7766f2c1aadb028010b9335e2065d- Stable URL of this page
https://metraipolis.com/documento/dc_a0cd3c96cb53
How to cite
SAC-GCL: Structure-Aware Compression for Graph Contrastive Learning — arXiv:2610.37898 — arXiv (en), https://arxiv.org/abs/2610.37898 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0cd3c96cb53 (Metraipolis archive dc_a0cd3c96cb53, sha256 30f2371de2c501fdbb68c498e10b46c96bb7766f2c1aadb028010b9335e2065d)
BibTeX
@misc{dca0cd3c96cb53,
title = {SAC-GCL: Structure-Aware Compression for Graph Contrastive Learning — arXiv:2610.37898},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.37898},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0cd3c96cb53; sha256 30f2371de2c501fdbb68c498e10b46c96bb7766f2c1aadb028010b9335e2065d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37898. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graph Contrastive Learning (GCL) has achieved remarkable success in self-supervised representation learning by maximizing agreement between augmented views of a graph. Although augmented view generation is the central step in GCL, existing models rely on stochastic augmentation of the input graph, such as edge perturbation and node masking, which lack structural awareness and frequently destroy critical topology or introduce semantically inconsistent views. While recent adaptive methods improve upon random perturbations, they primarily operate on localized node or edge neighborhoods and fail to capture higher-order, macro-level structural organization crucial for graph classification. To address this limitation, we propose Structure-aware Compression for Graph Contrastive Learning (SAC-GCL), a novel framework that employs structural decomposition and graph compression as a principled view generation strategy. Moving beyond random augmentations, SAC-GCL leverages structural decomposition techniques to extract cohesive subgraphs and condense them into supernodes, constructing coarsened graph views that preserve local density and capture higher-level structural patterns while reducing noise and redundancy. We leverage multiple cohesive subgraph models to derive complementary views of the graph, each capturing distinct structural properties. To capture multi-resolution information, a hierarchical view encoder processes these compressed views by initializing super-node features with shared-weight cohesive subgraph embeddings. Our results from extensive experiments on six benchmark datasets demonstrate that structure-aware compression provides a powerful alternative to random perturbations, yielding more robust and discriminative graph representations for graph classification tasks. Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.SI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Social and Information Networks (cs.SI). Pagina del lavoro: https://arxiv.org/abs/2610.37898 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-01T02:11:58.377Z dalla pagina https://arxiv.org/list/cs.SI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).