PiPE combines positional encodings with persistent homology features in a message-passing framework and is claimed to be provably more expressive than either approach alone, with empirical gains on molecular benchmarks.
Algebraic Topological Networks via the Persistent Local Homology Sheaf
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In this work, we introduce a novel approach based on algebraic topology to enhance graph convolution and attention modules by incorporating local topological properties of the data. To do so, we consider the framework of sheaf neural networks, which has been previously leveraged to incorporate additional structure into graph neural networks' features and construct more expressive, non-isotropic messages. Specifically, given an input simplicial complex (e.g. generated by the cliques of a graph or the neighbors in a point cloud), we construct its local homology sheaf, which assigns to each node the vector space of its local homology. The intermediate features of our networks live in these vector spaces and we leverage the associated sheaf Laplacian to construct more complex linear messages between them. Moreover, we extend this approach by considering the persistent version of local homology associated with a weighted simplicial complex (e.g., built from pairwise distances of nodes embeddings). This i) solves the problem of the lack of a natural choice of basis for the local homology vector spaces and ii) makes the sheaf itself differentiable, which enables our models to directly optimize the topology of their intermediate features.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Positional Encoding meets Persistent Homology on Graphs
PiPE combines positional encodings with persistent homology features in a message-passing framework and is claimed to be provably more expressive than either approach alone, with empirical gains on molecular benchmarks.