Pith. sign in

REVIEW 8 cited by

Architectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural Networks

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 2304.10031 v3 pith:LN55WEJ6 submitted 2023-04-20 cs.LG

classification cs.LG
keywords message-passingsystemstopologicalsocialarchitecturesdeepdevelopmentextract
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The natural world is full of complex systems characterized by intricate relations between their components: from social interactions between individuals in a social network to electrostatic interactions between atoms in a protein. Topological Deep Learning (TDL) provides a comprehensive framework to process and extract knowledge from data associated with these systems, such as predicting the social community to which an individual belongs or predicting whether a protein can be a reasonable target for drug development. TDL has demonstrated theoretical and practical advantages that hold the promise of breaking ground in the applied sciences and beyond. However, the rapid growth of the TDL literature for relational systems has also led to a lack of unification in notation and language across message-passing Topological Neural Network (TNN) architectures. This presents a real obstacle for building upon existing works and for deploying message-passing TNNs to new real-world problems. To address this issue, we provide an accessible introduction to TDL for relational systems, and compare the recently published message-passing TNNs using a unified mathematical and graphical notation. Through an intuitive and critical review of the emerging field of TDL, we extract valuable insights into current challenges and exciting opportunities for future development.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics

    cs.LG 2024-11 conditional novelty 7.0 of 10

    HOPNet uses combinatorial complex topology plus a physics-inspired message schedule to learn rigid body collisions, reporting lower rollout error and better OOD generalization than graph-based baselines.

  2. Cosmology with Topological Deep Learning

    astro-ph.CO 2025-05 conditional novelty 6.0 of 10

    Topological neural networks using tetrahedra, clusters and hyperedges built from halo catalogs lower inference error on Omega_m by 22% and on sigma_8 by up to 60% versus graph neural networks on Quijote.

  3. Quotient Complex Transformer (QCformer) for Perovskite Data Analysis

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Crystal structures encoded as quotient complexes with triangle features give improved perovskite bandgap prediction when processed by a simplex-based transformer.

  4. Heat Kernel Goes Topological

    cs.LG 2025-07 reject novelty 5.0 of 10

    TopoHKS defines a weighted combinatorial-complex Laplacian and heat kernel descriptor, claiming maximal expressive power; the supporting uniqueness theorem is incorrect.

  5. CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive Learning

    cs.LG 2025-05 conditional novelty 5.0 of 10

    CellCLAT applies parameter-perturbation contrastive learning to cellular complexes and adaptively trims 2-cells to improve downstream graph classification.

  6. EquiHGNN: Scalable Rotationally Equivariant Hypergraph Neural Networks

    cs.LG 2025-05 conditional novelty 4.0 of 10

    A plug-and-play combination of an equivariant GNN encoder and a hypergraph network with conjugated-bond hyperedges improves property prediction on large molecules, with inconsistent gains on small molecules.

  7. Relational inductive biases on attention mechanisms

    cs.LG 2025-07 conditional novelty 3.0 of 10

    Attention mechanisms are classified by their relational inductive bias: self-attention assumes a complete graph, masked attention a total order, strided attention p-previous connections, encoder-decoder a bipartite gr...

  8. 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