{"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/multiplicative-filter-networks","title":"Multiplicative Filter Networks","arxiv_id":null,"date":"2021-01-01","proceeding":"ICLR 2021 1","authors":["Rizal Fathony","Anit Kumar Sahu","Devin Willmott","J Zico Kolter"],"abstract":"Although deep networks are typically used to approximate functions over high dimensional inputs, recent work has increased interest in neural networks as function approximators for low-dimensional-but-complex functions, such as representing images as a function of pixel coordinates, solving differential equations, or representing signed distance fields or neural radiance fields.  Key to these recent successes has been the use of new elements such as sinusoidal nonlinearities, or Fourier features in positional encodings, which vastly outperform simple ReLU networks.  In this paper, we propose and empirically demonstrate that an arguably simpler class of function approximators can work just as well for such problems: multiplicative filter networks.  In these networks, we avoid traditional compositional depth altogether, and simply multiply together (linear functions of) sinusoidal or Gabor wavelet functions applied to the input.  This representation has the notable advantage that the entire function can simply be viewed as a linear function approximator over an exponential number of Fourier or Gabor basis functions, respectively.  Despite this simplicity, when compared to recent approaches that use Fourier features with ReLU networks or sinusoidal activation networks, we show that these multiplicative filter networks largely outperform or match the performance of these recent approaches on the domains highlighted in these past works.","url_abs":"https://openreview.net/forum?id=OmtmcPkkhT","url_pdf":"https://openreview.net/pdf?id=OmtmcPkkhT","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":"multiplicative-filter-networks","repo_url":"https://github.com/boschresearch/multiplicative-filter-networks","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"multiplicative-filter-networks","repo_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Multiplicative_Filter_Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"multiplicative-filter-networks","repo_url":"https://github.com/addy1997/mfn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"boschresearch/multiplicative-filter-networks","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MaximeVandegar/Papers-in-100-Lines-of-Code","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":33,"harvested_for":["1312.5602","1406.2661","1410.8516","1412.6980","1503.03585","1505.05770","1511.06434","1511.07289","1605.09782","1606.00704","1606.03498","1606.08415","1611.04076","1611.07004","1701.07875","1703.03400","1704.00028","1706.02515","1707.06347","1803.02999","1903.04057","2003.08934","2006.09661","2010.02502","2103.10380","2103.13744","2104.07970","2201.05989","2202.09778","2206.00927","2209.03003","2301.10241","2303.07418"],"harvested_for_calls":[{"arxiv_id":"1312.5602","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1312.5602"},"call":"get_harvested_code_for_paper(arxiv_id=\"1312.5602\")"},{"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\")"},{"arxiv_id":"1410.8516","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1410.8516"},"call":"get_harvested_code_for_paper(arxiv_id=\"1410.8516\")"},{"arxiv_id":"1412.6980","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1412.6980"},"call":"get_harvested_code_for_paper(arxiv_id=\"1412.6980\")"},{"arxiv_id":"1503.03585","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1503.03585"},"call":"get_harvested_code_for_paper(arxiv_id=\"1503.03585\")"},{"arxiv_id":"1505.05770","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1505.05770"},"call":"get_harvested_code_for_paper(arxiv_id=\"1505.05770\")"},{"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":"1511.07289","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1511.07289"},"call":"get_harvested_code_for_paper(arxiv_id=\"1511.07289\")"},{"arxiv_id":"1605.09782","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1605.09782"},"call":"get_harvested_code_for_paper(arxiv_id=\"1605.09782\")"},{"arxiv_id":"1606.00704","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.00704"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.00704\")"},{"arxiv_id":"1606.03498","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.03498"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.03498\")"},{"arxiv_id":"1606.08415","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.08415"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.08415\")"},{"arxiv_id":"1611.04076","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1611.04076"},"call":"get_harvested_code_for_paper(arxiv_id=\"1611.04076\")"},{"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":"1701.07875","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1701.07875"},"call":"get_harvested_code_for_paper(arxiv_id=\"1701.07875\")"},{"arxiv_id":"1703.03400","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1703.03400"},"call":"get_harvested_code_for_paper(arxiv_id=\"1703.03400\")"},{"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":"1706.02515","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.02515"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.02515\")"},{"arxiv_id":"1707.06347","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.06347"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.06347\")"},{"arxiv_id":"1803.02999","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.02999"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.02999\")"},{"arxiv_id":"1903.04057","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1903.04057"},"call":"get_harvested_code_for_paper(arxiv_id=\"1903.04057\")"},{"arxiv_id":"2003.08934","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.08934"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.08934\")"},{"arxiv_id":"2006.09661","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.09661"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.09661\")"},{"arxiv_id":"2010.02502","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.02502"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.02502\")"},{"arxiv_id":"2103.10380","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.10380"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.10380\")"},{"arxiv_id":"2103.13744","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.13744"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.13744\")"},{"arxiv_id":"2104.07970","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.07970"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.07970\")"},{"arxiv_id":"2201.05989","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2201.05989"},"call":"get_harvested_code_for_paper(arxiv_id=\"2201.05989\")"},{"arxiv_id":"2202.09778","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.09778"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.09778\")"},{"arxiv_id":"2206.00927","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2206.00927"},"call":"get_harvested_code_for_paper(arxiv_id=\"2206.00927\")"},{"arxiv_id":"2209.03003","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2209.03003"},"call":"get_harvested_code_for_paper(arxiv_id=\"2209.03003\")"},{"arxiv_id":"2301.10241","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.10241"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.10241\")"},{"arxiv_id":"2303.07418","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.07418"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.07418\")"}]},{"repo":"addy1997/mfn-pytorch","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":"1547c59a24e0457ab4ab463724ff719c1193cdc04213c892365ae1d3774835ed","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}