Proceedings

GraphReach: Position-Aware Graph Neural Network using Reachability Estimations

Sunil Nishad, Shubhangi Agarwal, Arnab Bhattacharya, Sayan Ranu

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1527-1533.

https://doi.org/10.24963/ijcai.2021/211

Keywords

  • Data Mining: Mining Graphs, Semi Structured Data, Complex Data

Abstract

Majority of the existing graph neural networks(GNN) learn node embeddings that encode their local neighborhoods but not their positions. Consequently, two nodes that are vastly distant but located in similar local neighborhoods map to similar embeddings in those networks. This limitation prevents accurate performance in predictive tasks that rely on position information. In this paper, we develop GRAPHREACH , a position-aware inductive GNN that captures the global positions of nodes through reachability estimations with respect to a set of anchor nodes. The anchors are strategically selected so that reachability estimations across all the nodes are maximized. We show that this combinatorial anchor selection problem is NP-hard and, consequently, develop a greedy (1−1/e) approximation heuristic. Empirical evaluation against state-of-the-art GNN architectures reveal that GRAPHREACH provides up to 40% relative improvement in accuracy. In addition, it is more robust to adversarial attacks.

Sunil Nishad, Shubhangi Agarwal, Arnab Bhattacharya, and Sayan Ranu. 2021. GraphReach: Position-Aware Graph Neural Network using Reachability Estimations. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1527–1533. https://doi.org/10.24963/ijcai.2021/211
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards