{"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/graph-neural-networks-with-learnable-and","title":"Graph Neural Networks with Learnable and Optimal Polynomial Bases","arxiv_id":"2302.12432","date":"2023-02-24","proceeding":null,"authors":["Yuhe Guo","Zhewei Wei"],"abstract":"Polynomial filters, a kind of Graph Neural Networks, typically use a predetermined polynomial basis and learn the coefficients from the training data. It has been observed that the effectiveness of the model is highly dependent on the property of the polynomial basis. Consequently, two natural and fundamental questions arise: Can we learn a suitable polynomial basis from the training data? Can we determine the optimal polynomial basis for a given graph and node features? In this paper, we propose two spectral GNN models that provide positive answers to the questions posed above. First, inspired by Favard's Theorem, we propose the FavardGNN model, which learns a polynomial basis from the space of all possible orthonormal bases. Second, we examine the supposedly unsolvable definition of optimal polynomial basis from Wang & Zhang (2022) and propose a simple model, OptBasisGNN, which computes the optimal basis for a given graph structure and graph signal. Extensive experiments are conducted to demonstrate the effectiveness of our proposed models. Our code is available at https://github.com/yuziGuo/FarOptBasis.","url_abs":"https://arxiv.org/abs/2302.12432v2","url_pdf":"https://arxiv.org/pdf/2302.12432v2.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":"graph-neural-networks-with-learnable-and","repo_url":"https://github.com/yuziGuo/FarOptBasis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-classification-on-non-homophilic","task_name":"Node Classification on Non-Homophilic (Heterophilic) Graphs"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-film-60-20-20-random","task":"Node Classification","dataset":"Film (60%/20%/20% random splits)","model":"FavardGNN","rank_in_archive_order":3,"of":37,"metrics":{"1:1 Accuracy":"43.05 ± 0.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-film-60-20-20-random","task":"Node Classification","dataset":"Film (60%/20%/20% random splits)","model":"OptBasisGNN","rank_in_archive_order":4,"of":37,"metrics":{"1:1 Accuracy":"42.39 ± 0.52"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pokec","task":"Node Classification","dataset":"pokec","model":"OptBasisGNN","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"82.83±0.04"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-non-homophilic-14","task":"Node Classification on Non-Homophilic (Heterophilic) Graphs","dataset":"genius","model":"OptBasisGNN","rank_in_archive_order":9,"of":26,"metrics":{"1:1 Accuracy":"90.83±0.11"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.12432","atlas_url":"https://app.syntology.ai/?focus=2302.12432","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2302.12432"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2302.12432\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2302.12432"},"call":"get_concepts_for_paper(arxiv_id=\"2302.12432\")"}],"by_repo":[{"repo":"yuziGuo/FarOptBasis","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"9e45e5565ad562a921e87886b96d5be46421c07c9f706afd7725a38fed0706f0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}