{"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/fdgatii-fast-dynamic-graph-attention-with","title":"FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping","arxiv_id":"2110.11464","date":"2021-10-21","proceeding":null,"authors":["Gayan K. Kulatilleke","Marius Portmann","Ryan Ko","Shekhar S. Chandra"],"abstract":"While Graph Neural Networks have gained popularity in multiple domains, graph-structured input remains a major challenge due to (a) over-smoothing, (b) noisy neighbours (heterophily), and (c) the suspended animation problem. To address all these problems simultaneously, we propose a novel graph neural network FDGATII, inspired by attention mechanism's ability to focus on selective information supplemented with two feature preserving mechanisms. FDGATII combines Initial Residuals and Identity Mapping with the more expressive dynamic self-attention to handle noise prevalent from the neighbourhoods in heterophilic data sets. By using sparse dynamic attention, FDGATII is inherently parallelizable in design, whist efficient in operation; thus theoretically able to scale to arbitrary graphs with ease. Our approach has been extensively evaluated on 7 datasets. We show that FDGATII outperforms GAT and GCN based benchmarks in accuracy and performance on fully supervised tasks, obtaining state-of-the-art results on Chameleon and Cornell datasets with zero domain-specific graph pre-processing, and demonstrate its versatility and fairness.","url_abs":"https://arxiv.org/abs/2110.11464v2","url_pdf":"https://arxiv.org/pdf/2110.11464v2.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":"fdgatii-fast-dynamic-graph-attention-with","repo_url":"https://github.com/gayanku/FDGATII","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"gat","method_name":"GAT"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"FDGATII","rank_in_archive_order":46,"of":61,"metrics":{"Accuracy":"65.1754"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-full","task":"Node Classification","dataset":"Citeseer Full-supervised","model":"FDGATII","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"75.6434%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-full-supervised","task":"Node Classification","dataset":"Cora Full-supervised","model":"FDGATII","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"87.7867%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"FDGATII","rank_in_archive_order":34,"of":60,"metrics":{"Accuracy":"82.4324"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-full-supervised","task":"Node Classification","dataset":"Pubmed Full-supervised","model":"FDGATII","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy":"90.3524%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"FDGATII","rank_in_archive_order":49,"of":62,"metrics":{"Accuracy":"80.5405"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"FDGATII","rank_in_archive_order":39,"of":63,"metrics":{"Accuracy":"86.2745"},"uses_additional_data":false}],"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":"gayanku/FDGATII","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1710.10903"],"harvested_for_calls":[{"arxiv_id":"1710.10903","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.10903"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.10903\")"}]}],"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":"02b7d32db27b73d46a0b3260b98556c1363648f13013107ca324838b73177440","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}