Representation & Self-Supervised Learning

Contrastive/self-supervised learning, embeddings, transfer & domain adaptation.

A topic in the Science corpus, drawn from 2,548 papers.

Trusted voices in Representation & Self-Supervised Learning

Ordered by the trust Representation & Self-Supervised Learning's own network concentrates on each researcher, most first.

  1. Alex Krizhevsky — trusted by 5,744 researchers here
  2. Geoffrey E. Hinton — trusted by 4,475 researchers here
  3. Yoshua Bengio — trusted by 3,513 researchers here
  4. L. V. D. van der Maaten — trusted by 2,432 researchers here
  5. Tomas Mikolov — trusted by 2,148 researchers here
  6. Richard Socher — trusted by 2,169 researchers here
  7. Christopher D. Manning — trusted by 2,090 researchers here
  8. Radford M. Neal — trusted by 1,757 researchers here
  9. Andrew Y. Ng — trusted by 1,761 researchers here
  10. Ruslan Salakhutdinov — trusted by 1,523 researchers here
  11. Jeffrey Pennington — trusted by 1,577 researchers here
  12. R. Caruana — trusted by 1,133 researchers here

Most-cited papers in Representation & Self-Supervised Learning

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Learning Transferable Visual Models From Natural Language Supervision (2021, International Conference on Machine Learning) — 52,559 citations
  2. Visualizing Data using t-SNE (2008) — 50,192 citations
  3. Learning Multiple Layers of Features from Tiny Images (2009) — 43,276 citations
  4. Pattern Recognition and Machine Learning (2006) — 40,958 citations
  5. Semi-Supervised Classification with Graph Convolutional Networks (2016, International Conference on Learning Representations) — 36,100 citations
  6. Distributed Representations of Words and Phrases and their Compositionality (2013, Neural Information Processing Systems) — 35,459 citations
  7. GloVe: Global Vectors for Word Representation (2014) — 34,790 citations
  8. Efficient Estimation of Word Representations in Vector Space (2013) — 34,723 citations
  9. Principal Component Analysis (2003) — 27,017 citations
  10. A Simple Framework for Contrastive Learning of Visual Representations (2020, International Conference on Machine Learning) — 25,300 citations
  11. A Survey on Transfer Learning (2010) — 23,590 citations
  12. Inductive Representation Learning on Large Graphs (2017, Neural Information Processing Systems) — 20,392 citations
  13. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019) — 19,155 citations
  14. Nonlinear dimensionality reduction by locally linear embedding. (2000) — 16,021 citations
  15. Momentum Contrast for Unsupervised Visual Representation Learning (2019, Computer Vision and Pattern Recognition) — 15,360 citations
  16. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns (2002) — 15,301 citations
  17. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (2017) — 14,813 citations
  18. Segment Anything (2023, IEEE International Conference on Computer Vision) — 14,627 citations
  19. Representation Learning: A Review and New Perspectives (2012) — 14,067 citations
  20. Representation Learning with Contrastive Predictive Coding (2018) — 13,907 citations
  21. Principal Component Analysis (2002) — 13,002 citations
  22. A global geometric framework for nonlinear dimensionality reduction. (2000) — 12,870 citations
  23. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction (2018) — 12,836 citations
  24. node2vec: Scalable Feature Learning for Networks (2016) — 12,391 citations
  25. Deep Contextualized Word Representations (2018, North American Chapter of the Association for Computational Linguistics) — 12,212 citations
  26. Masked Autoencoders Are Scalable Vision Learners (2021, Computer Vision and Pattern Recognition) — 12,173 citations
  27. A survey on Image Data Augmentation for Deep Learning (2019) — 11,876 citations
  28. Domain-Adversarial Training of Neural Networks (2015) — 11,758 citations
  29. Enriching Word Vectors with Subword Information (2016) — 10,838 citations
  30. DeepWalk: online learning of social representations (2014) — 10,831 citations
  31. On Spectral Clustering: Analysis and an algorithm (2001) — 10,805 citations
  32. Tensor Decompositions and Applications (2009) — 10,682 citations
  33. Prototypical Networks for Few-shot Learning (2017) — 10,206 citations
  34. Distributed Representations of Sentences and Documents (2014) — 9,778 citations
  35. Emerging Properties in Self-Supervised Vision Transformers (2021, IEEE International Conference on Computer Vision) — 9,706 citations
  36. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013) — 9,576 citations
  37. Algorithms for Non-negative Matrix Factorization (2000) — 9,381 citations
  38. How transferable are features in deep neural networks? (2014) — 9,349 citations
  39. Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks (2006) — 9,072 citations
  40. Translating Embeddings for Modeling Multi-relational Data (2013) — 9,012 citations
  41. Learning Deep Architectures for AI (2007) — 8,849 citations
  42. Unsupervised Cross-lingual Representation Learning at Scale (2019) — 8,807 citations
  43. Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (2020) — 8,797 citations
  44. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation (2003) — 8,581 citations
  45. Matching Networks for One Shot Learning (2016) — 8,487 citations
  46. Extracting and composing robust features with denoising autoencoders (2008) — 8,231 citations
  47. UMAP: Uniform Manifold Approximation and Projection (2018) — 7,959 citations
  48. Neural Discrete Representation Learning (2017) — 7,634 citations
  49. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion (2010) — 7,579 citations
  50. Learning to Forget: Continual Prediction with LSTM (2000) — 7,541 citations

Most active researchers

By papers in this topic: a volume measure, not trust.