{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/softmax-gan","title":"Softmax GAN","arxiv_id":"1704.06191","date":"2017-04-20","proceeding":null,"authors":["Min Lin"],"abstract":"Softmax GAN is a novel variant of Generative Adversarial Network (GAN). The key idea of Softmax GAN is to replace the classification loss in the original GAN with a softmax cross-entropy loss in the sample space of one single batch. In the adversarial learning of $N$ real training samples and $M$ generated samples, the target of discriminator training is to distribute all the probability mass to the real samples, each with probability $\\frac{1}{M}$, and distribute zero probability to generated data. In the generator training phase, the target is to assign equal probability to all data points in the batch, each with probability $\\frac{1}{M+N}$. While the original GAN is closely related to Noise Contrastive Estimation (NCE), we show that Softmax GAN is the Importance Sampling version of GAN. We futher demonstrate with experiments that this simple change stabilizes GAN training.","url_abs":"https://arxiv.org/abs/1704.06191v2","url_pdf":"https://arxiv.org/pdf/1704.06191v2.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":"softmax-gan","repo_url":"https://github.com/eriklindernoren/PyTorch-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"softmax-gan","repo_url":"https://github.com/korra141/Generative-Adversarial-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"softmax-gan","repo_url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/flownet2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"softmax-gan","repo_url":"https://github.com/MindSpore-paper-code-3/code7/tree/main/gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"eriklindernoren/PyTorch-GAN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":14,"harvested_for":["1511.05644","1511.06434","1604.07379","1606.03657","1609.03126","1611.06430","1611.07004","1702.08431","1703.00848","1704.00028","1704.02510","1705.07215","1711.09020","1809.03627"],"harvested_for_calls":[{"arxiv_id":"1511.05644","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.05644"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.05644\")"},{"arxiv_id":"1511.06434","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.06434"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.06434\")"},{"arxiv_id":"1604.07379","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1604.07379"},"call":"get_harvested_code_for_paper(arxiv_id=\"1604.07379\")"},{"arxiv_id":"1606.03657","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.03657"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.03657\")"},{"arxiv_id":"1609.03126","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.03126"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.03126\")"},{"arxiv_id":"1611.06430","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1611.06430"},"call":"get_harvested_code_for_paper(arxiv_id=\"1611.06430\")"},{"arxiv_id":"1611.07004","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1611.07004"},"call":"get_harvested_code_for_paper(arxiv_id=\"1611.07004\")"},{"arxiv_id":"1702.08431","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08431"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08431\")"},{"arxiv_id":"1703.00848","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1703.00848"},"call":"get_harvested_code_for_paper(arxiv_id=\"1703.00848\")"},{"arxiv_id":"1704.00028","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1704.00028"},"call":"get_harvested_code_for_paper(arxiv_id=\"1704.00028\")"},{"arxiv_id":"1704.02510","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1704.02510"},"call":"get_harvested_code_for_paper(arxiv_id=\"1704.02510\")"},{"arxiv_id":"1705.07215","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1705.07215"},"call":"get_harvested_code_for_paper(arxiv_id=\"1705.07215\")"},{"arxiv_id":"1711.09020","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.09020"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.09020\")"},{"arxiv_id":"1809.03627","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1809.03627"},"call":"get_harvested_code_for_paper(arxiv_id=\"1809.03627\")"}]},{"repo":"korra141/Generative-Adversarial-Networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1406.2661"],"harvested_for_calls":[{"arxiv_id":"1406.2661","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1406.2661"},"call":"get_harvested_code_for_paper(arxiv_id=\"1406.2661\")"}]},{"repo":"MindSpore-paper-code-3/code4","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-paper-code-3/code7","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"647812ece684aef2457f138b23332046d285b44fd8a221871fd78625217734dc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}