{"url":"/sota/representation-learning-on-scidocs","task":{"name":"Representation Learning","url":"/task/representation-learning","note":null},"dataset":{"name":"SciDocs","url":"/dataset/scidocs"},"category":"Computer Vision","categories":["Computer Vision","Methodology","Natural Language Processing"],"category_note":null,"description":"**Representation Learning**  is a process in machine learning where algorithms extract meaningful patterns from raw data to create representations that are easier to understand and process. These representations can be designed for interpretability, reveal hidden features, or be used for transfer learning. They are valuable across many fundamental machine learning tasks like [image classification](/task/image-classification) and [retrieval](/task/image-retrieval).\r\n\r\nDeep neural networks can be considered representation learning models that typically encode information which is projected into a different subspace. These representations are then usually passed on to a linear classifier to, for instance, train a classifier. \r\n\r\nRepresentation learning can be divided into:\r\n\r\n-  **Supervised representation learning**: learning representations on task A using annotated data and used to solve task B\r\n- **Unsupervised representation learning**: learning representations on a task in an unsupervised way (label-free data). These are then used to address downstream tasks and reducing the need for annotated data when learning news tasks. Powerful models like [GPT](/method/gpt) and [BERT](/method/bert) leverage unsupervised representation learning to tackle language tasks.  \r\n\r\nMore recently, [self-supervised learning (SSL)](/task/self-supervised-learning) is one of the main drivers behind unsupervised representation learning in fields like computer vision and NLP. \r\n\r\nHere are some additional readings to go deeper on the task:\r\n\r\n- [Representation Learning: A Review and New Perspectives](/paper/representation-learning-a-review-and-new) - Bengio et al. (2012)\r\n- [A Few Words on Representation Learning](https://sthalles.github.io/a-few-words-on-representation-learning/) - Thalles Silva\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Visualizing and Understanding Convolutional Networks](https://arxiv.org/pdf/1311.2901.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Avg."],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Avg.":null}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SciNCL","metrics":{"Avg.":"81.8"},"uses_additional_data":false,"paper_date":"2022-02-14","paper":"/paper/neighborhood-contrastive-learning-for-1","paper_url":"https://arxiv.org/abs/2202.06671v2","paper_title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","code":"https://github.com/malteos/scincl","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"SPECTER","metrics":{"Avg.":"80.0"},"uses_additional_data":false,"paper_date":"2020-04-15","paper":"/paper/document-level-representation-learning-using","paper_url":"https://arxiv.org/abs/2004.07180v4","paper_title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","code":"https://github.com/allenai/specter","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":3,"model":"Citeomatic","metrics":{"Avg.":"76.0"},"uses_additional_data":false,"paper_date":"2020-04-15","paper":"/paper/document-level-representation-learning-using","paper_url":"https://arxiv.org/abs/2004.07180v4","paper_title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","code":"https://github.com/allenai/specter","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"Sci-DeCLUTR","metrics":{"Avg.":"66.6"},"uses_additional_data":false,"paper_date":"2022-02-14","paper":"/paper/neighborhood-contrastive-learning-for-1","paper_url":"https://arxiv.org/abs/2202.06671v2","paper_title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","code":"https://github.com/malteos/scincl","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"SciBERT","metrics":{"Avg.":"59.6"},"uses_additional_data":false,"paper_date":"2020-04-15","paper":"/paper/document-level-representation-learning-using","paper_url":"https://arxiv.org/abs/2004.07180v4","paper_title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","code":"https://github.com/allenai/specter","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"BioBERT","metrics":{"Avg.":"58.8"},"uses_additional_data":false,"paper_date":"2019-01-25","paper":"/paper/biobert-a-pre-trained-biomedical-language","paper_url":"https://arxiv.org/abs/1901.08746v4","paper_title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","code":"https://github.com/dmis-lab/biobert","n_code_links":19,"syntology":{"n_ran":4,"n_unverified":21,"n_samples":25,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"CiteBERT","metrics":{"Avg.":"58.8"},"uses_additional_data":false,"paper_date":"2022-02-14","paper":"/paper/neighborhood-contrastive-learning-for-1","paper_url":"https://arxiv.org/abs/2202.06671v2","paper_title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","code":"https://github.com/malteos/scincl","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":5,"n_unverified":22,"n_samples":27,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":24,"n_samples":31,"n_pointer_only_licence":4,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}