{"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/adaptive-graph-diffusion-networks-with-hop","title":"Adaptive Graph Diffusion Networks","arxiv_id":"2012.15024","date":"2020-12-30","proceeding":null,"authors":["Chuxiong Sun","Jie Hu","Hongming Gu","Jinpeng Chen","MingChuan Yang"],"abstract":"Graph Neural Networks (GNNs) have received much attention in the graph deep learning domain. However, recent research empirically and theoretically shows that deep GNNs suffer from over-fitting and over-smoothing problems. The usual solutions either cannot solve extensive runtime of deep GNNs or restrict graph convolution in the same feature space. We propose the Adaptive Graph Diffusion Networks (AGDNs) which perform multi-layer generalized graph diffusion in different feature spaces with moderate complexity and runtime. Standard graph diffusion methods combine large and dense powers of the transition matrix with predefined weighting coefficients. Instead, AGDNs combine smaller multi-hop node representations with learnable and generalized weighting coefficients. We propose two scalable mechanisms of weighting coefficients to capture multi-hop information: Hop-wise Attention (HA) and Hop-wise Convolution (HC). We evaluate AGDNs on diverse, challenging Open Graph Benchmark (OGB) datasets with semi-supervised node classification and link prediction tasks. Until the date of submission (Aug 26, 2022), AGDNs achieve top-1 performance on the ogbn-arxiv, ogbn-proteins and ogbl-ddi datasets and top-3 performance on the ogbl-citation2 dataset. On the similar Tesla V100 GPU cards, AGDNs outperform Reversible GNNs (RevGNNs) with 13% complexity and 1% training runtime of RevGNNs on the ogbn-proteins dataset. AGDNs also achieve comparable performance to SEAL with 36% training and 0.2% inference runtime of SEAL on the ogbl-citation2 dataset.","url_abs":"https://arxiv.org/abs/2012.15024v2","url_pdf":"https://arxiv.org/pdf/2012.15024v2.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":"adaptive-graph-diffusion-networks-with-hop","repo_url":"https://github.com/skepsun/SAGN_with_SLE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-property-prediction-on-ogbl-citation2","task":"Link Property Prediction","dataset":"ogbl-citation2","model":"AGDN w/GraphSAINT","rank_in_archive_order":12,"of":23,"metrics":{"Ext. data":"No","Number of params":"306716","Test MRR":"0.8549 ± 0.0029","Validation MRR":"0.8556 ± 0.0033"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ddi","task":"Link Property Prediction","dataset":"ogbl-ddi","model":"AGDN (AUC loss)","rank_in_archive_order":5,"of":31,"metrics":{"Ext. data":"No","Number of params":"3506691","Test Hits@20":"0.9538 ± 0.0094","Validation Hits@20":"0.8943 ± 0.0281"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ppa","task":"Link Property Prediction","dataset":"ogbl-ppa","model":"AGDN","rank_in_archive_order":17,"of":26,"metrics":{"Ext. data":"No","Number of params":"36904259","Test Hits@100":"0.4123 ± 0.0159","Validation Hits@100":"0.4332 ± 0.0092"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GIANT-XRT+AGDN+BoT+self-KD","rank_in_archive_order":8,"of":86,"metrics":{"Ext. data":"Yes","Number of params":"1309760","Test Accuracy":"0.7637 ± 0.0011","Validation Accuracy":"0.7719 ± 0.0008"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"GIANT-XRT+AGDN+BoT","rank_in_archive_order":12,"of":86,"metrics":{"Ext. data":"Yes","Number of params":"1309760","Test Accuracy":"0.7618 ± 0.0016","Validation Accuracy":"0.7724 ± 0.0006"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"AGDN+BoT+self-KD+C&S","rank_in_archive_order":20,"of":86,"metrics":{"Ext. data":"No","Number of params":"1513294","Test Accuracy":"0.7431 ± 0.0014","Validation Accuracy":"0.7518 ± 0.0009"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"AGDN+BoT+self-KD","rank_in_archive_order":21,"of":86,"metrics":{"Ext. data":"No","Number of params":"1513294","Test Accuracy":"0.7428 ± 0.0017","Validation Accuracy":"0.7526 ± 0.0001"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"AGDN+BoT","rank_in_archive_order":27,"of":86,"metrics":{"Ext. data":"No","Number of params":"1513294","Test Accuracy":"0.7410 ± 0.0015","Validation Accuracy":"0.7522 ± 0.0007"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"AGDN (GAT-HA+3_heads+labels)","rank_in_archive_order":31,"of":86,"metrics":{"Ext. data":"No","Number of params":"1508555","Test Accuracy":"0.7398 ± 0.0009","Validation Accuracy":"0.7519 ± 0.0009"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-arxiv","task":"Node Property Prediction","dataset":"ogbn-arxiv","model":"AGDN (GAT-HA+3_heads)","rank_in_archive_order":37,"of":86,"metrics":{"Ext. data":"No","Number of params":"1447115","Test Accuracy":"0.7375 ± 0.0021","Validation Accuracy":"0.7483 ± 0.0009"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-products","task":"Node Property Prediction","dataset":"ogbn-products","model":"AGDN","rank_in_archive_order":29,"of":64,"metrics":{"Ext. data":"No","Number of params":"1544047","Test Accuracy":"0.8334 ± 0.0027","Validation Accuracy":"0.9229 ± 0.0010"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"AGDN","rank_in_archive_order":3,"of":26,"metrics":{"Ext. data":"No","Number of params":"8605486","Test ROC-AUC":"0.8865 ± 0.0013","Validation ROC-AUC":"0.9418 ± 0.0005"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.15024","atlas_url":"https://app.syntology.ai/?focus=2012.15024","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":"2012.15024"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.15024\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.15024"},"call":"get_concepts_for_paper(arxiv_id=\"2012.15024\")"}],"by_repo":[{"repo":"skepsun/SAGN_with_SLE","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2104.09376"],"harvested_for_calls":[{"arxiv_id":"2104.09376","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.09376"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.09376\")"}]}],"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":"eda94db4efd2c90c2d7a34315c46c768aa0004de989b352c467ef236d9af7d96","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}