mlsanityData to 7 Oct 2026

Parallel Algorithms Align with Neural Execution

arXiv 2307.04049 ↗First posted 8 Jul 2023cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Neural algorithmic reasoners are parallel processors. Teaching them sequential algorithms contradicts this nature, rendering a significant share of their computations redundant. Parallel algorithms however may exploit their full computational power, therefore requiring fewer layers to be executed. This drastically reduces training times, as we observe when comparing parallel implementations of searching, sorting and finding strongly connected components to their sequential counterparts on the CLRS framework. Additionally, parallel versions achieve (often strongly) superior predictive performance.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 8 Jul 2023.

Builds on

21 of 33 references.

References · 21

  1. 2017Graph Attention Networkscited by 8,854
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2017Deep Setscited by 1,394
  4. 2015Recent Advances in Convolutional Neural Networkscited by 360
  5. 2019What graph neural networks cannot learn: depth vs widthcited by 195
  6. 2019What Can Neural Networks Reason About?cited by 155
  7. 2015Neural GPUs Learn Algorithmscited by 118
  8. 2022The CLRS Algorithmic Reasoning Benchmarkcited by 103
  9. 2021Neural Algorithmic Reasoningcited by 92
  10. 2022A Generalist Neural Algorithmic Learnercited by 58
  11. 2022Graph Neural Networks are Dynamic Programmerscited by 55
  12. 2020Pointer Graph Networkscited by 52
9 more
  1. 2021An Evaluation of Edge TPU Accelerators for Convolutional Neural Networkscited by 39
  2. 2020Neural Execution Engines: Learning to Execute Subroutinescited by 36
  3. 2021Differentiable Sorting Networks for Scalable Sorting and Ranking Supervisioncited by 31
  4. 2023Neural Algorithmic Reasoning with Causal Regularisationcited by 30
  5. 2022Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Taskscited by 29
  6. 2018Recent Advances in Convolutional Neural Network Accelerationcited by 17
  7. 2021Reasoning-Modulated Representationscited by 13
  8. 2021Algorithmic Concept-based Explainable Reasoningcited by 12
  9. 2020A step towards neural genome assemblycited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 2.

6 papers.

  1. 2024Simulation of Graph Algorithms with Looped Transformerscited by 29
  2. 2023SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoningcited by 11
  3. 2025Primal-Dual Neural Algorithmic Reasoningcited by 8
  4. 2024Recurrent Aggregators in Neural Algorithmic Reasoningcited by 6
  5. 2024Deep Equilibrium Algorithmic Reasoningcited by 4
  6. 2025Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encodingcited by 4