mlsanityData to 7 Oct 2026

The Responsibility Problem in Neural Networks with Unordered Targets

arXiv 2304.09499 ↗First posted 19 Apr 2023cs.LG cs.DMcited by 4

Not on the map. Why?

Abstract (arXiv)

We discuss the discontinuities that arise when mapping unordered objects to neural network outputs of fixed permutation, referred to as the responsibility problem. Prior work has proved the existence of the issue by identifying a single discontinuity. Here, we show that discontinuities under such models are uncountably infinite, motivating further research into neural networks for unordered data.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 3 of its 6 references that are in the map. First posted on arXiv 19 Apr 2023.

Builds on

3 of 6 references.

References · 3

  1. 2019FSPool: Learning Set Representations with Featurewise Sort Poolingcited by 53
  2. 2018Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networkscited by 6
  3. 2020Learning Sub-Patterns in Piecewise Continuous Functionscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 3.

4 papers.

  1. 2023Object-centric architectures enable efficient causal representation learningcited by 21
  2. 2025Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matchingcited by 6
  3. 2025Mechanistic Independence: A Principle for Identifiable Disentangled Representationscited by 3
  4. 2025Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Priorcited by 0