mlsanityData to 14 Oct 2026

A Short Survey of Systematic Generalization

arXiv 2211.11956 ↗First posted 22 Nov 2022cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This survey includes systematic generalization and a history of how machine learning addresses it. We aim to summarize and organize the related information of both conventional and recent improvements. We first look at the definition of systematic generalization, then introduce Classicist and Connectionist. We then discuss different types of Connectionists and how they approach the generalization. Two crucial problems of variable binding and causality are discussed. We look into systematic generalization in language, vision, and VQA fields. Recent improvements from different aspects are discussed. Systematic generalization has a long history in artificial intelligence. We could cover only a small portion of many contributions. We hope this paper provides a background and is beneficial for discoveries in future work.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 133 of its 243 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

133 of 243 references.

References · 133

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  6. 2015VQA: Visual Question Answeringcited by 2,506
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  9. 2019Invariant Risk Minimizationcited by 1,854
  10. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  11. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  12. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
38 more
  1. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  2. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 968
  3. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  4. 2015Pointer Networkscited by 895
  5. 2020Object-Centric Learning with Slot Attentioncited by 876
  6. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  7. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  8. 2021Domain Generalization: A Surveycited by 764
  9. 2014Neural Turing Machinescited by 644
  10. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  11. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  12. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  13. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  14. 2015Neural Module Networkscited by 376
  15. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 372
  16. 2016Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependenciescited by 354
  17. 2017A simple neural network module for relational reasoningcited by 346
  18. 2017Embodied Question Answeringcited by 336
  19. 2018Understanding disentangling in β-VAEcited by 335
  20. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 335
  21. 2018Towards a Definition of Disentangled Representationscited by 296
  22. 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 284
  23. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 275
  24. 2020COGS: A Compositional Generalization Challenge Based on Semantic Interpretationcited by 263
  25. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  26. 2019Recurrent Independent Mechanismscited by 219
  27. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  28. 2013Learning Bayesian Networks: The Combination of Knowledge and Statistical Datacited by 187
  29. 2018Compositional Attention Networks for Machine Reasoningcited by 183
  30. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  31. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  32. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  33. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 163
  34. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  35. 2019Good-Enough Compositional Data Augmentationcited by 158
  36. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  37. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  38. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 151

50 most cited of 133 All 133 (JSON)

Built on by

Not cited yet.