Permutation-Invariant Learning

Overview

Permutation-invariant learning studies how to model unordered inputs, such as point clouds, molecules, particle systems, tables, and candidate lists, without making predictions depend on arbitrary ordering. Common approaches include Deep Sets and pooling-based encoders, Set Transformers, matching-based losses, group symmetrization, and training objectives that encourage consistency across permutations. These methods support tasks such as classification, generation, retrieval, and prediction of unordered collections, sometimes using equivariant layers when outputs should reorder along with inputs. A central challenge is balancing exact symmetry guarantees and computational cost with preserving useful structure, especially when some forms of order are meaningful or learned robustness is incomplete.

Latest papers

CardsList

34 papers2 papers in the last four weeks, down 71% on the four weeks before. 0.0% of all new papers.

  1. Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits

    Dec 16, 2025Michael Murray, Tenzin Chan, Kedar Karhadker +1Sample ComplexityNeural Network Memorization

  2. NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation

    Dec 5, 2025Daniel Rose, Roxane Axel Jacob, Johannes Kirchmair +13D Molecular GenerationAutoregressive Transformer

  3. Strengthening LLMs for Tabular Prediction with Structural Priors

    Oct 20, 2025Pengxiang Cai, Zihao Gao, Wanchen Lian +2Tabular Foundation ModelsRL for Language Models

  4. Challenges in Non-Polymeric Crystal Structure Prediction: Why a Geometric, Permutation-Invariant Loss is Needed

    Aug 31, 2025Emmanuel Jehanno, Romain Menegaux, Julien Mairal +1Crystal Structure PredictionPermutation-Invariant Learning