Lying Graph Convolution: Learning to Lie for Node Classification Tasks
This addresses a domain-specific challenge in graph machine learning by enhancing adaptability for node classification tasks, though it is incremental as it builds on existing GCN frameworks.
The paper tackles the problem of node classification in graphs with heterophilic (dissimilar adjacent nodes) and homophilic (similar adjacent nodes) structures by introducing Lying-GCN, a Deep Graph Network that adaptively allows nodes to lie when sharing embeddings, resulting in improved performance in heterophilic settings without degrading homophilic results.
In the context of machine learning for graphs, many researchers have empirically observed that Deep Graph Networks (DGNs) perform favourably on node classification tasks when the graph structure is homophilic (\ie adjacent nodes are similar). In this paper, we introduce Lying-GCN, a new DGN inspired by opinion dynamics that can adaptively work in both the heterophilic and the homophilic setting. At each layer, each agent (node) shares its own opinions (node embeddings) with its neighbours. Instead of sharing its opinion directly as in GCN, we introduce a mechanism which allows agents to lie. Such a mechanism is adaptive, thus the agents learn how and when to lie according to the task that should be solved. We provide a characterisation of our proposal in terms of dynamical systems, by studying the spectral property of the coefficient matrix of the system. While the steady state of the system collapses to zero, we believe the lying mechanism is still usable to solve node classification tasks. We empirically prove our belief on both synthetic and real-world datasets, by showing that the lying mechanism allows to increase the performances in the heterophilic setting without harming the results in the homophilic one.