Graph Filtration Learning
This work addresses graph classification problems for researchers and practitioners in machine learning, representing an incremental improvement in readout operations for graph neural networks.
The paper tackles graph classification by introducing a novel readout operation that aggregates node features into graph-level representations using persistent homology with a learnable filter function, showing favorable empirical performance compared to previous techniques, particularly when graph connectivity is informative.
We propose an approach to learning with graph-structured data in the problem domain of graph classification. In particular, we present a novel type of readout operation to aggregate node features into a graph-level representation. To this end, we leverage persistent homology computed via a real-valued, learnable, filter function. We establish the theoretical foundation for differentiating through the persistent homology computation. Empirically, we show that this type of readout operation compares favorably to previous techniques, especially when the graph connectivity structure is informative for the learning problem.