mlsanityData to 7 Oct 2026

A Survey on Compositional Generalization in Applications

arXiv 2302.01067 ↗First posted 2 Feb 2023cs.AI cs.LG cs.SCcited by 12

Not on the map. Why?

Abstract (arXiv)

The field of compositional generalization is currently experiencing a renaissance in AI, as novel problem settings and algorithms motivated by various practical applications are being introduced, building on top of the classical compositional generalization problem. This article aims to provide a comprehensive review of top recent developments in multiple real-life applications of the compositional generalization. Specifically, we introduce a taxonomy of common applications and summarize the state-of-the-art for each of those domains. Furthermore, we identify important current trends and provide new perspectives pertaining to the future of this burgeoning field.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 16 of its 46 references that are in the map. First posted on arXiv 2 Feb 2023.

Builds on

16 of 46 references.

References · 16

  1. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  2. 2020COGS: A Compositional Generalization Challenge Based on Semantic Interpretationcited by 260
  3. 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 123
  4. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  5. 2019Human few-shot learning of compositional instructionscited by 47
  6. 2022Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Languagecited by 42
  7. 2021On Compositional Generalization of Neural Machine Translationcited by 34
  8. 2019Compositional Generalization in Image Captioningcited by 23
  9. 2022Policy Architectures for Compositional Generalization in Controlcited by 23
  10. 2022Toward Compositional Generalization in Object-Oriented World Modelingcited by 22
  11. 2022Compositional Multi-Object Reinforcement Learning with Linear Relation Networkscited by 19
  12. 2022SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learningcited by 8
4 more
  1. 2022Knowledge Management System with NLP-Assisted Annotations: A Brief Survey and Outlookcited by 7
  2. 2021Grounded Graph Decoding Improves Compositional Generalization in Question Answeringcited by 6
  3. 2022Lightweight Compositional Embeddings for Incremental Streaming Recommendationcited by 3
  4. 2022Improving Compositional Generalization in Math Word Problem Solvingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 4.

12 papers.

  1. 2024Entity-Centric Reinforcement Learning for Object Manipulation from Pixelscited by 27
  2. 2024On Provable Length and Compositional Generalizationcited by 22
  3. 2025Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologiescited by 17
  4. 2024Compositional Risk Minimizationcited by 13
  5. 2024Entity-based Reinforcement Learning for Autonomous Cyber Defencecited by 11
  6. 2024EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generationcited by 8
  7. 2026Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusioncited by 6
  8. 2024Controllable Image Generation with Composed Parallel Token Predictioncited by 0
  9. 2025Disassociating performance from compositional feature learningcited by 0
  10. 2026Controllable Image Generation with Composed Parallel Token Predictioncited by 0
  11. 2026Grounding vs. Compositionality: On the Non-Complementarity of Reasoning in Neuro-Symbolic Systemscited by 0
  12. 2026Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulationcited by 0