mlsanityData to 7 Oct 2026

Learning Symbolic Representations Through Joint GEnerative and DIscriminative Training

arXiv 2304.11357 ↗First posted 22 Apr 2023cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

We introduce GEDI, a Bayesian framework that combines existing self-supervised learning objectives with likelihood-based generative models. This framework leverages the benefits of both GEnerative and DIscriminative approaches, resulting in improved symbolic representations over standalone solutions. Additionally, GEDI can be easily integrated and trained jointly with existing neuro-symbolic frameworks without the need for additional supervision or costly pre-training steps. We demonstrate through experiments on real-world data, including SVHN, CIFAR10, and CIFAR100, that GEDI outperforms existing self-supervised learning strategies in terms of clustering performance by a significant margin. The symbolic component further allows it to leverage knowledge in the form of logical constraints to improve performance in the small data regime.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 22 Apr 2023.

Builds on

25 of 33 references.

References · 25

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  5. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  6. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  7. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  8. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  9. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  10. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  11. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  12. 2020Whitening for Self-Supervised Representation Learningcited by 278
13 more
  1. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  2. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  3. 2016A Theory of Generative ConvNetcited by 174
  4. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 147
  5. 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
  6. 2021Solo-learn: A Library of Self-supervised Methods for Visual Representation Learningcited by 116
  7. 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
  8. 2020No MCMC for me: Amortized sampling for fast and stable training of energy-based modelscited by 64
  9. 2022Self-Supervised Learning with an Information Maximization Criterioncited by 38
  10. 2022Self-Supervised Learning via Maximum Entropy Codingcited by 33
  11. 2019Making sense of sensory inputcited by 29
  12. 2022Energy-Based Contrastive Learning of Visual Representationscited by 13
  13. 2022GEDI: GEnerative and DIscriminative Training for Self-Supervised Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 1; 2026: 1.

8 papers.

  1. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
  2. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  3. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  4. 2024Collapse-Proof Non-Contrastive Self-Supervised Learningcited by 7
  5. 2023The Triad of Failure Modes and a Possible Way Outcited by 3
  6. 2023Unifying Self-Supervised Clustering and Energy-Based Modelscited by 2
  7. 2026Differentiable Rule Induction from Raw Sequence Inputscited by 2
  8. 2024Bridging the Gap: Representation Spaces in Neuro-Symbolic AIcited by 0