mlsanityData to 14 Oct 2026

Learning to Reason with Third-Order Tensor Products

arXiv 1811.12143 ↗First posted 29 Nov 2018cs.LG cs.NE stat.MLcited by 27

Not on the map. Why?

Abstract (arXiv)

We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data. This improves symbolic interpretation and systematic generalisation. Our architecture is trained end-to-end through gradient descent on a variety of simple natural language reasoning tasks, significantly outperforming the latest state-of-the-art models in single-task and all-tasks settings. We also augment a subset of the data such that training and test data exhibit large systematic differences and show that our approach generalises better than the previous state-of-the-art.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 5; 2024: 6; 2025: 2; 2026: 2.

27 papers.

Sort:

By area:

  1. 2021Linear Transformers Are Secretly Fast Weight Programmerscited by 502
  2. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
  3. 2022StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Textscited by 68
  4. 2023Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Textcited by 59
  5. 2022Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systemscited by 44
  6. 2021Learning with Holographic Reduced Representationscited by 25
  7. 2023Recasting Self-Attention with Holographic Reduced Representationscited by 14
  8. 2021Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarizationcited by 11
  9. 2024Consecutive Batch Model Editing with HooK Layerscited by 10
  10. 2024Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architecturescited by 9
  11. 2024Towards Learning Abductive Reasoning using VSA Distributed Representationscited by 9
  12. 2025Fast weight programming and linear transformers: from machine learning to neurobiologycited by 8
15 more
  1. 2021On the Memory Mechanism of Tensor-Power Recurrent Modelscited by 5
  2. 2022Structural Biases for Improving Transformers on Translation into Morphologically Rich Languagescited by 5
  3. 2023Differentiable Tree Operations Promote Compositional Generalizationcited by 5
  4. 2022Meta-Reinforcement Learning with Self-Modifying Networkscited by 4
  5. 2022Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networkscited by 4
  6. 2023Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representationscited by 4
  7. 2024A Walsh Hadamard Derived Linear Vector Symbolic Architecturecited by 4
  8. 2023DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Textcited by 3
  9. 2024Attention-based Iterative Decomposition for Tensor Product Representationcited by 2
  10. 2022Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networkscited by 1
  11. 2026Tensor Product Representation Probes Reveal Shared Structure Across Linear Directionscited by 1
  12. 2021PAC-learning gains of Turing machines over circuits and neural networkscited by 0
  13. 2024Discrete Dictionary-based Decomposition Layer for Structured Representation Learningcited by 0
  14. 2025Who invented deep residual learning?cited by 0
  15. 2026Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modelingcited by 0