{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/teaching-a-gan-what-not-to-learn","title":"Teaching a GAN What Not to Learn","arxiv_id":"2010.15639","date":"2020-10-29","proceeding":"NeurIPS 2020 12","authors":["Siddarth Asokan","Chandra Sekhar Seelamantula"],"abstract":"Generative adversarial networks (GANs) were originally envisioned as unsupervised generative models that learn to follow a target distribution. Variants such as conditional GANs, auxiliary-classifier GANs (ACGANs) project GANs on to supervised and semi-supervised learning frameworks by providing labelled data and using multi-class discriminators. In this paper, we approach the supervised GAN problem from a different perspective, one that is motivated by the philosophy of the famous Persian poet Rumi who said, \"The art of knowing is knowing what to ignore.\" In the GAN framework, we not only provide the GAN positive data that it must learn to model, but also present it with so-called negative samples that it must learn to avoid - we call this \"The Rumi Framework.\" This formulation allows the discriminator to represent the underlying target distribution better by learning to penalize generated samples that are undesirable - we show that this capability accelerates the learning process of the generator. We present a reformulation of the standard GAN (SGAN) and least-squares GAN (LSGAN) within the Rumi setting. The advantage of the reformulation is demonstrated by means of experiments conducted on MNIST, Fashion MNIST, CelebA, and CIFAR-10 datasets. Finally, we consider an application of the proposed formulation to address the important problem of learning an under-represented class in an unbalanced dataset. The Rumi approach results in substantially lower FID scores than the standard GAN frameworks while possessing better generalization capability.","url_abs":"https://arxiv.org/abs/2010.15639v1","url_pdf":"https://arxiv.org/pdf/2010.15639v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"teaching-a-gan-what-not-to-learn","repo_url":"https://github.com/DarthSid95/RumiGANs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"philosophy","task_name":"Philosophy"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.15639","atlas_url":"https://app.syntology.ai/?focus=2010.15639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15639"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DarthSid95/RumiGANs","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b9da61c36d3b8f11","entry":"compute_prd","repo":"DarthSid95/RumiGANs","repo_kind":"official","path":"ext_resources/prd_score.py","file_url":"https://github.com/DarthSid95/RumiGANs/blob/HEAD/ext_resources/prd_score.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9da61c36d3b8f11"}},{"code_sha256_prefix":"5d84440e02c3a502","entry":"compute_prd_from_embedding","repo":"DarthSid95/RumiGANs","repo_kind":"official","path":"ext_resources/prd_score.py","file_url":"https://github.com/DarthSid95/RumiGANs/blob/HEAD/ext_resources/prd_score.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d84440e02c3a502"}},{"code_sha256_prefix":"5adbefd0ebfa3e5e","entry":"prd_to_max_f_beta_pair","repo":"DarthSid95/RumiGANs","repo_kind":"official","path":"ext_resources/prd_score.py","file_url":"https://github.com/DarthSid95/RumiGANs/blob/HEAD/ext_resources/prd_score.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5adbefd0ebfa3e5e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}