Pith. sign in

REVIEW 1 cited by

From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.16174 v2 pith:MONVFSXC submitted 2023-05-25 cs.LG cs.AIcs.NE

classification cs.LGcs.AIcs.NE
keywords graphcellcomplexinferencelatenttopologyinputlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networks (GNNs) on a given graph topology by dynamically learning it. However, most of LGI methods assume to have a (noisy, incomplete, improvable, ...) input graph to rewire and can solely learn regular graph topologies. In the wake of the success of Topological Deep Learning (TDL), we study Latent Topology Inference (LTI) for learning higher-order cell complexes (with sparse and not regular topology) describing multi-way interactions between data points. To this aim, we introduce the Differentiable Cell Complex Module (DCM), a novel learnable function that computes cell probabilities in the complex to improve the downstream task. We show how to integrate DCM with cell complex message passing networks layers and train it in a end-to-end fashion, thanks to a two-step inference procedure that avoids an exhaustive search across all possible cells in the input, thus maintaining scalability. Our model is tested on several homophilic and heterophilic graph datasets and it is shown to outperform other state-of-the-art techniques, offering significant improvements especially in cases where an input graph is not provided.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Topological Signal Processing and Learning: Recent Advances and Future Challenges

    eess.SP 2024-12 accept novelty 2.0 of 10

    A survey of topological signal processing and learning that uses Hodge theory to unify recent advances in processing signals on simplicial and cell complexes.

Pith tools