MyJournals Home  

RSS FeedsEntropy, Vol. 24, Pages 1745: Graph Multihead Attention Pooling with Self-Supervised Learning (Entropy)


29 november 2022 11:58:52

Entropy, Vol. 24, Pages 1745: Graph Multihead Attention Pooling with Self-Supervised Learning (Entropy)

Graph neural networks (GNNs), which work with graph-structured data, have attracted considerable attention and achieved promising performance on graph-related tasks. While the majority of existing GNN methods focus on the convolutional operation for encoding the node representations, the graph pooling operation, which maps the set of nodes into a coarsened graph, is crucial for graph-level tasks. We argue that a well-defined graph pooling operation should avoid the information loss of the local node features and global graph structure. In this paper, we propose a hierarchical graph pooling method based on the multihead attention mechanism, namely GMAPS, which compresses both node features and graph structure into the coarsened graph. Specifically, a multihead attention mechanism is adopted to arrange nodes into a coarsened graph based on their features and structural dependencies between nodes. In addition, to enhance the expressiveness of the cluster representations, a self-supervised mechanism is introduced to maximize the mutual information between the cluster representations and the global representation of the hierarchical graph. Our experimental results show that the proposed GMAPS obtains significant and consistent performance improvements compared with state-of-the-art baselines on six benchmarks from the biological and social domains of graph classification and reconstruction tasks.

60 viewsCategory: Informatics, Physics
Entropy, Vol. 24, Pages 1743: Towards Quantum Control with Advanced Quantum Computing: A Perspective (Entropy)
Entropy, Vol. 24, Pages 1746: Models for Quantum Measurement of Particles with Higher Spin (Entropy)
blog comments powered by Disqus
The latest issues of all your favorite science journals on one page


Register | Retrieve



Copyright © 2008 - 2023 Indigonet Services B.V.. Contact: Tim Hulsen. Read here our privacy notice.
Other websites of Indigonet Services B.V.: Nieuws Vacatures News Tweets Nachrichten