Graph Parsing Networks

arXiv:2402.14393v1 Announce Type: new
Abstract: Graph pooling compresses graph information into a compact representation. State-of-the-art graph pooling methods follow a hierarchical approach, which reduces the graph size step-by-step. These methods must balance memory efficiency with preserving node information, depending on whether they use node dropping or node clustering. Additionally, fixed pooling ratios or numbers of pooling layers are predefined for all graphs, which prevents personalized pooling structures from being captured for each individual graph. In this work, inspired by bottom-up …

abstract art arxiv balance clustering cs.lg efficiency graph hierarchical information memory networks node numbers parsing pooling representation state step-by-step type