mlsanityData to 7 Oct 2026

Compositional Generalization by Learning Analytical Expressions

arXiv 2006.10627 ↗First posted 18 Jun 2020cs.AI cs.CLcited by 53

Not on the map. Why?

Abstract (arXiv)

Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily. However, existing neural network based models have been proven to be extremely deficient in such a capability. Inspired by work in cognition which argues compositionality can be captured by variable slots with symbolic functions, we present a refreshing view that connects a memory-augmented neural model with analytical expressions, to achieve compositional generalization. Our model consists of two cooperative neural modules, Composer and Solver, fitting well with the cognitive argument while being able to be trained in an end-to-end manner via a hierarchical reinforcement learning algorithm. Experiments on the well-known benchmark SCAN demonstrate that our model seizes a great ability of compositional generalization, solving all challenges addressed by previous works with 100% accuracies.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 14; 2023: 12; 2024: 7; 2025: 3.

53 papers.

Sort:

By area:

  1. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  2. 2021The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformerscited by 117
  3. 2023Randomized Positional Encodings Boost Length Generalization of Transformerscited by 114
  4. 2022Compositional Semantic Parsing with Large Language Modelscited by 95
  5. 2021Making Transformers Solve Compositional Taskscited by 72
  6. 2021The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalizationcited by 62
  7. 2024ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficultycited by 60
  8. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  9. 2023How Do In-Context Examples Affect Compositional Generalization?cited by 51
  10. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  11. 2021Improving Compositional Generalization with Latent Structure and Data Augmentationcited by 46
  12. 2021Learning Algebraic Recombination for Compositional Generalizationcited by 31
38 more
  1. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  2. 2021Lexicon Learning for Few-Shot Neural Sequence Modelingcited by 28
  3. 2021Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalizationcited by 27
  4. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  5. 2021Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Taskscited by 19
  6. 2023ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesiscited by 17
  7. 2024Can Models Learn Skill Composition from Examples?cited by 17
  8. 2022Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignmentcited by 16
  9. 2021Modeling Hierarchical Structures with Continuous Recursive Neural Networkscited by 15
  10. 2022Neural-Symbolic Recursive Machine for Systematic Generalizationcited by 12
  11. 2022Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Modelscited by 10
  12. 2021Learning Symbolic Rules for Reasoning in Quasi-Natural Languagecited by 9
  13. 2022Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionalitycited by 8
  14. 2021Compositional Generalization for Natural Language Interfaces to Web APIscited by 7
  15. 2023MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretationscited by 7
  16. 2021A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semanticscited by 6
  17. 2021Learning to Generalize Compositionally by Transferring Across Semantic Parsing Taskscited by 6
  18. 2022Compositional Generalization and Decomposition in Neural Program Synthesiscited by 6
  19. 2023Does Deep Learning Learn to Abstract? A Systematic Probing Frameworkcited by 6
  20. 2023Beam Tree Recursive Cellscited by 6
  21. 2024Towards Understanding the Relationship between In-context Learning and Compositional Generalizationcited by 5
  22. 2024What makes Models Compositional? A Theoretical View: With Supplementcited by 5
  23. 2023Efficient Beam Tree Recursioncited by 4
  24. 2023Compositional Program Generation for Few-Shot Systematic Generalizationcited by 4
  25. 2022Equivariant Transduction through Invariant Alignmentcited by 3
  26. 2023Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalizationcited by 3
  27. 2021Distributionally Robust Recurrent Decoders with Random Network Distillationcited by 2
  28. 2023Semantic-aware Contrastive Learning for More Accurate Semantic Parsingcited by 2
  29. 2023Layer-wise Representation Fusion for Compositional Generalizationcited by 2
  30. 2023Harnessing Dataset Cartography for Improved Compositional Generalization in Transformerscited by 2
  31. 2025HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Dronescited by 2
  32. 2022Measuring Alignment Bias in Neural Seq2Seq Semantic Parserscited by 1
  33. 2024Consistency of Compositional Generalization across Multiple Levelscited by 1
  34. 2021Concepts, Properties and an Approach for Compositional Generalizationcited by 0
  35. 2022Learning Invariable Semantical Representation from Language for Extensible Policy Generalizationcited by 0
  36. 2022Tackling Math Word Problems with Fine-to-Coarse Abstracting and Reasoningcited by 0
  37. 2022A Short Survey of Systematic Generalizationcited by 0
  38. 2024Machine Learning and Data Analysis Using Posets: A Surveycited by 0

50 most cited of 53 All 53 (JSON)