On permutation-invariant neural networks

arXiv:2403.17410v1 Announce Type: new
Abstract: Conventional machine learning algorithms have traditionally been designed under the assumption that input data follows a vector-based format, with an emphasis on vector-centric paradigms. However, as the demand for tasks involving set-based inputs has grown, there has been a paradigm shift in the research community towards addressing these challenges. In recent years, the emergence of neural network architectures such as Deep Sets and Transformers has presented a significant advancement in the treatment of set-based data. …

abstract algorithms arxiv challenges community cs.ai cs.lg data demand format however inputs machine machine learning machine learning algorithms networks neural networks paradigm research research community set shift stat.ml tasks type vector