DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
This addresses the need for flexible and adaptive activation functions in GNNs, offering an incremental improvement for graph data processing.
The paper tackled the problem of designing activation functions for Graph Neural Networks (GNNs) by proposing DiGRAF, a graph-adaptive diffeomorphic activation function, which demonstrated consistent and superior performance across diverse datasets and tasks compared to traditional and graph-specific activation functions.
In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs). Motivated by the need for graph-adaptive and flexible activation functions, we introduce DiGRAF, leveraging Continuous Piecewise-Affine Based (CPAB) transformations, which we augment with an additional GNN to learn a graph-adaptive diffeomorphic activation function in an end-to-end manner. In addition to its graph-adaptivity and flexibility, DiGRAF also possesses properties that are widely recognized as desirable for activation functions, such as differentiability, boundness within the domain, and computational efficiency. We conduct an extensive set of experiments across diverse datasets and tasks, demonstrating a consistent and superior performance of DiGRAF compared to traditional and graph-specific activation functions, highlighting its effectiveness as an activation function for GNNs. Our code is available at https://github.com/ipsitmantri/DiGRAF.