Multiple Kernel Representation Learning on Networks

Abdulkadir Çelikkanat (1, 2, 3, 4) , Yanning Shen (5) , Fragkiskos D. Malliaros (1, 2, 3)

1 CVN - Centre de vision numérique
2 OPIS - OPtimisation Imagerie et Santé
3 Université Paris-Saclay
4 DTU Compute - Department of Applied Mathematics and Computer Science [Lyngby]
5 UC Irvine - University of California [Irvine]

Learning representations of nodes in a low dimensional space is a crucial task with numerous interesting applications in network analysis, including link prediction, node classification, and visualization. Two popular approaches for this problem are matrix factorization and random walk-based models. In this paper, we aim to bring together the best of both worlds, towards learning node representations. In particular, we propose a weighted matrix factorization model that encodes random walk-based information about nodes of the network. The benefit of this novel formulation is that it enables us to utilize kernel functions without realizing the exact proximity matrix so that it enhances the expressiveness of existing matrix decomposition methods with kernels and alleviates their computational complexities. We extend the approach with a multiple kernel learning formulation that provides the flexibility of learning the kernel as the linear combination of a dictionary of kernels in data-driven fashion. We perform an empirical evaluation on real-world networks, showing that the proposed model outperforms baseline node embedding algorithms in downstream machine learning tasks.

Mots clés: link prediction; node classification; kernel methods; node embeddings; Graph representation learning

Domaines: Apprentissage [cs.LG]; Réseaux sociaux et d'information [cs.SI]

Abdulkadir Çelikkanat, Yanning Shen, Fragkiskos D. Malliaros. Multiple Kernel Representation Learning on Networks. IEEE Transactions on Knowledge and Data Engineering, In press, ⟨10.1109/tkde.2022.3172048⟩. ⟨hal-03686085⟩