PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information. Prior works have proposed a variety of graph rewiring concepts that aim at optimizing the spatial or spectral properties of graphs to promote the signal propagation. However, such approaches inevitably deteriorate the original graph topology, which may lead to a distortion of information flow. To address this, we introduce an expanded width-aware (PANDA) message passing, a new message passing paradigm where nodes with high centrality, a potential source of over-squashing, are selectively expanded in width to encapsulate the growing influx of signals from distant nodes. Experimental results show that our method outperforms existing rewiring methods, suggesting that selectively expanding the hidden state of nodes can be a compelling alternative to graph rewiring for addressing the over-squashing.
Code (1)
Tasks
Graph ClassificationGraph Neural NetworkGraph RegressionNode ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PyPanda: a Python Package for Gene Regulatory Network Reconstruction
PANDA (Passing Attributes between Networks for Data Assimilation) is a gene regulatory network inference method that uses message-passing to integrate multiple sources of 'omics data. PANDA was originally coded in C++. I…
High Performance Computing of Gene Regulatory Networks using a Message-Passing Model
Gene regulatory network reconstruction is a fundamental problem in computational biology. We recently developed an algorithm, called PANDA (Passing Attributes Between Networks for Data Assimilation), that integrates mult…
C++ codeComputational EfficiencyHigher-Order Expander Graph Propagation
Graph neural networks operate on graph-structured data via exchanging messages along edges. One limitation of this message passing paradigm is the over-squashing problem. Over-squashing occurs when messages from a node's…
Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning. In contrast to existing models, embedding-based or path-based, we learn an input-dependent subgraph to explicitly …
Knowledge Base CompletionUnbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network
Recent scene graph generation (SGG) frameworks have focused on learning complex relationships among multiple objects in an image. Thanks to the nature of the message passing neural network (MPNN) that models high-order i…
Graph GenerationRelationRepresentation LearningScene Graph Generation