Higher-order Clustering and Pooling for Graph Neural Networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Higher-order Clustering and Pooling for Graph Neural Networks

Résumé

Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings hierarchically into a final graph representation. However, they are not only questioned by recent work showing on par performance with random pooling, but also ignore completely higher-order connectivity patterns. To tackle this issue, we propose HoscPool, a clustering-based graph pooling operator that captures higher-order information hierarchically, leading to richer graph representations. In fact, we learn a probabilistic cluster assignment matrix end-to-end by minimising relaxed formulations of motif spectral clustering in our objective function, and we then extend it to a pooling operator. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure, achieving best performance. Lastly, we provide a deep empirical analysis of pooling operators' inner functioning.
Fichier principal
Vignette du fichier
2209.03473.pdf (800.45 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03910823 , version 1 (22-01-2024)

Identifiants

Citer

Alexandre Duval, Fragkiskos D. Malliaros. Higher-order Clustering and Pooling for Graph Neural Networks. CIKM 2022 - 31st ACM International Conference on Information & Knowledge Management, Oct 2022, Atlanta, Georgia, United States. pp.426-435, ⟨10.1145/3511808.3557353⟩. ⟨hal-03910823⟩
44 Consultations
4 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More