{"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/diffusion-jump-gnns-homophiliation-via","title":"Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters","arxiv_id":"2306.16976","date":"2023-06-29","proceeding":null,"authors":["Ahmed Begga","Francisco Escolano","Miguel Angel Lozano","Edwin R. Hancock"],"abstract":"High-order Graph Neural Networks (HO-GNNs) have been developed to infer consistent latent spaces in the heterophilic regime, where the label distribution is not correlated with the graph structure. However, most of the existing HO-GNNs are hop-based, i.e., they rely on the powers of the transition matrix. As a result, these architectures are not fully reactive to the classification loss and the achieved structural filters have static supports. In other words, neither the filters' supports nor their coefficients can be learned with these networks. They are confined, instead, to learn combinations of filters. To address the above concerns, we propose Diffusion-jump GNNs a method relying on asymptotic diffusion distances that operates on jumps. A diffusion-pump generates pairwise distances whose projections determine both the support and coefficients of each structural filter. These filters are called jumps because they explore a wide range of scales in order to find bonds between scattered nodes with the same label. Actually, the full process is controlled by the classification loss. Both the jumps and the diffusion distances react to classification errors (i.e. they are learnable). Homophiliation, i.e., the process of learning piecewise smooth latent spaces in the heterophilic regime, is formulated as a Dirichlet problem: the known labels determine the border nodes and the diffusion-pump ensures a minimal deviation of the semi-supervised grouping from a canonical unsupervised grouping. This triggers the update of both the diffusion distances and, consequently, the jumps in order to minimize the classification error. The Dirichlet formulation has several advantages. It leads to the definition of structural heterophily, a novel measure beyond edge heterophily. It also allows us to investigate links with (learnable) diffusion distances, absorbing random walks and stochastic diffusion.","url_abs":"https://arxiv.org/abs/2306.16976v1","url_pdf":"https://arxiv.org/pdf/2306.16976v1.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":"diffusion-jump-gnns-homophiliation-via","repo_url":"https://github.com/AhmedBegggaUA/TFM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"DJ-GNN","rank_in_archive_order":30,"of":62,"metrics":{"Accuracy":"36.93 ± 0.84"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"DJ-GNN","rank_in_archive_order":1,"of":61,"metrics":{"Accuracy":"80.48±1.46"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"DJ-GNN","rank_in_archive_order":6,"of":60,"metrics":{"Accuracy":"87.03±1.62"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-penn94","task":"Node Classification","dataset":"Penn94","model":"DJ-GNN","rank_in_archive_order":9,"of":32,"metrics":{"Accuracy":"84.84±0.34"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"DJ-GNN","rank_in_archive_order":6,"of":59,"metrics":{"Accuracy":"73.48±1.59"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"DJ-GNN","rank_in_archive_order":5,"of":62,"metrics":{"Accuracy":"92.43±3.15"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"DJ-GNN","rank_in_archive_order":3,"of":63,"metrics":{"Accuracy":"\t92.54±3.70"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-arxiv-year","task":"Node Classification","dataset":"arXiv-year","model":"DJ-GNN","rank_in_archive_order":11,"of":12,"metrics":{"Accuracy":"49.21±0.20"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.16976","atlas_url":"https://app.syntology.ai/?focus=2306.16976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16976"}},"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/AhmedBegggaUA/TFM","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"3cf45ebe3b517745","entry":"pump","repo":"AhmedBegggaUA/TFM","repo_kind":"official","path":"pump.py","file_url":"https://github.com/AhmedBegggaUA/TFM/blob/HEAD/pump.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3cf45ebe3b517745"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}