{"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/gans-can-play-lottery-tickets-too-1","title":"GANs Can Play Lottery Tickets Too","arxiv_id":"2106.00134","date":"2021-05-31","proceeding":"ICLR 2021 1","authors":["Xuxi Chen","Zhenyu Zhang","Yongduo Sui","Tianlong Chen"],"abstract":"Deep generative adversarial networks (GANs) have gained growing popularity in numerous scenarios, while usually suffer from high parameter complexities for resource-constrained real-world applications. However, the compression of GANs has less been explored. A few works show that heuristically applying compression techniques normally leads to unsatisfactory results, due to the notorious training instability of GANs. In parallel, the lottery ticket hypothesis shows prevailing success on discriminative models, in locating sparse matching subnetworks capable of training in isolation to full model performance. In this work, we for the first time study the existence of such trainable matching subnetworks in deep GANs. For a range of GANs, we certainly find matching subnetworks at 67%-74% sparsity. We observe that with or without pruning discriminator has a minor effect on the existence and quality of matching subnetworks, while the initialization weights used in the discriminator play a significant role. We then show the powerful transferability of these subnetworks to unseen tasks. Furthermore, extensive experimental results demonstrate that our found subnetworks substantially outperform previous state-of-the-art GAN compression approaches in both image generation (e.g. SNGAN) and image-to-image translation GANs (e.g. CycleGAN). Codes available at https://github.com/VITA-Group/GAN-LTH.","url_abs":"https://arxiv.org/abs/2106.00134v1","url_pdf":"https://arxiv.org/pdf/2106.00134v1.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":"gans-can-play-lottery-tickets-too-1","repo_url":"https://github.com/VITA-Group/GAN-LTH","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.00134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00134"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/VITA-Group/GAN-LTH","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"d8301c10a2c6eab7","entry":"calculate_activation_statistics","repo":"VITA-Group/GAN-LTH","repo_kind":"official","path":"src/CycleGAN/fid_score.py","file_url":"https://github.com/VITA-Group/GAN-LTH/blob/HEAD/src/CycleGAN/fid_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8301c10a2c6eab7"}},{"code_sha256_prefix":"0def50a351111624","entry":"calculate_frechet_distance","repo":"VITA-Group/GAN-LTH","repo_kind":"official","path":"src/CycleGAN/fid_score.py","file_url":"https://github.com/VITA-Group/GAN-LTH/blob/HEAD/src/CycleGAN/fid_score.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0def50a351111624"}},{"code_sha256_prefix":"f0714ae9daec4654","entry":"get_activations","repo":"VITA-Group/GAN-LTH","repo_kind":"official","path":"src/CycleGAN/fid_score.py","file_url":"https://github.com/VITA-Group/GAN-LTH/blob/HEAD/src/CycleGAN/fid_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f0714ae9daec4654"}},{"code_sha256_prefix":"88b148114932e7a9","entry":"rewind_weight","repo":"VITA-Group/GAN-LTH","repo_kind":"official","path":"src/CycleGAN/prun_utils.py","file_url":"https://github.com/VITA-Group/GAN-LTH/blob/HEAD/src/CycleGAN/prun_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88b148114932e7a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}