{"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":"/method/gin","slug":"gin","name":"GIN","full_name":"Graph Isomorphism Network","full_name_withheld":false,"description_markdown":"Per the authors, Graph Isomorphism Network (GIN) generalizes the WL test and hence achieves maximum discriminative power among GNNs.","description_state":"present","introduced_year":null,"introduced_by":{"title":"How Powerful are Graph Neural Networks?","paper":"/paper/how-powerful-are-graph-neural-networks","first_author":"Keyulu Xu","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/how-powerful-are-graph-neural-networks"},"source":{"url":"http://arxiv.org/abs/1810.00826v3","title":"How Powerful are Graph Neural Networks?","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Models","url":"/methods/category/graph-models","pwc_aliases":[]},{"area":"Graphs","area_id":"graphs","collection":"Graph Embeddings","url":"/methods/category/graph-embeddings","pwc_aliases":[]}],"n_papers_tagged":43,"archive_num_papers":43,"papers_newest_first":[{"paper":null,"slug":"evaluating-loss-functions-for-graph-neural","title":"Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization","date":"2025-06-17","arxiv_id":"2506.14114","n_code_links":0,"syntology":null},{"paper":"/paper/2505-10711","slug":"2505-10711","title":"GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics","date":"2025-05-15","arxiv_id":"2505.10711","n_code_links":1,"syntology":null},{"paper":null,"slug":"robustness-questions-the-interpretability-of","title":"Robustness questions the interpretability of graph neural networks: what to do?","date":"2025-05-05","arxiv_id":"2505.02566","n_code_links":0,"syntology":null},{"paper":"/paper/unlocking-the-potential-of-classic-gnns-for","slug":"unlocking-the-potential-of-classic-gnns-for","title":"Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence","date":"2025-02-13","arxiv_id":"2502.09263","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":3,"n_instrument":4,"unverified":5,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["LUOyk1999/GNNPlus"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/densegnn-universal-and-scalable-deeper-graph","slug":"densegnn-universal-and-scalable-deeper-graph","title":"DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules","date":"2025-01-05","arxiv_id":"2501.03278","n_code_links":1,"syntology":null},{"paper":"/paper/graph-aware-isomorphic-attention-for-adaptive","slug":"graph-aware-isomorphic-attention-for-adaptive","title":"Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers","date":"2025-01-04","arxiv_id":"2501.02393","n_code_links":1,"syntology":null},{"paper":null,"slug":"communication-efficient-personalized-federal","title":"Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition","date":"2024-12-18","arxiv_id":"2412.13442","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-half-precision-for-gnn-training","title":"Using Half-Precision for GNN Training","date":"2024-11-02","arxiv_id":"2411.01109","n_code_links":0,"syntology":null},{"paper":"/paper/an-analysis-of-novel-money-laundering-data","slug":"an-analysis-of-novel-money-laundering-data","title":"An Analysis of Novel Money Laundering Data Using Heterogeneous Graph Isomorphism Networks. FinCEN Files Case Study","date":"2024-07-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"tackling-oversmoothing-in-gnn-via-graph","title":"Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach","date":"2024-07-16","arxiv_id":"2407.11928","n_code_links":0,"syntology":null},{"paper":"/paper/network-analytics-for-anti-money-laundering-a","slug":"network-analytics-for-anti-money-laundering-a","title":"Network Analytics for Anti-Money Laundering -- A Systematic Literature Review and Experimental Evaluation","date":"2024-05-29","arxiv_id":"2405.19383","n_code_links":1,"syntology":null},{"paper":"/paper/nana-and-migu-semantic-data-augmentation","slug":"nana-and-migu-semantic-data-augmentation","title":"NaNa and MiGu: Semantic Data Augmentation Techniques to Enhance Protein Classification in Graph Neural Networks","date":"2024-03-21","arxiv_id":"2403.14736","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-and-yet-fairly-effective-defense-for","slug":"a-simple-and-yet-fairly-effective-defense-for","title":"A Simple and Yet Fairly Effective Defense for Graph Neural Networks","date":"2024-02-21","arxiv_id":"2402.13987","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sennadir/noisygnn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-power-of-graph-neural-networks-and","slug":"on-the-power-of-graph-neural-networks-and","title":"On the Power of Graph Neural Networks and Feature Augmentation Strategies to Classify Social Networks","date":"2024-01-11","arxiv_id":"2401.06048","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-adversarial-robustness-of-graph","title":"On the Adversarial Robustness of Graph Contrastive Learning Methods","date":"2023-11-29","arxiv_id":"2311.17853","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-genetic-improvement-mutations-using","slug":"enhancing-genetic-improvement-mutations-using","title":"Enhancing Genetic Improvement Mutations Using Large Language Models","date":"2023-10-18","arxiv_id":"2310.19813","n_code_links":1,"syntology":null},{"paper":"/paper/graph-isomorphic-networks-for-assessing","slug":"graph-isomorphic-networks-for-assessing","title":"Graph Isomorphic Networks for Assessing Reliability of the Medium-Voltage Grid","date":"2023-10-02","arxiv_id":"2310.01181","n_code_links":1,"syntology":null},{"paper":null,"slug":"gin-generative-invariant-shape-prior-for","title":"GIN: Generative INvariant Shape Prior for Amodal Instance Segmentation","date":"2023-09-22","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/inkstream-real-time-gnn-inference-on","slug":"inkstream-real-time-gnn-inference-on","title":"InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update","date":"2023-09-20","arxiv_id":"2309.11071","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-independent-noise-condition-for-1","title":"Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables","date":"2023-08-13","arxiv_id":"2308.06718","n_code_links":0,"syntology":null},{"paper":"/paper/h2cgl-modeling-dynamics-of-citation-network","slug":"h2cgl-modeling-dynamics-of-citation-network","title":"H2CGL: Modeling Dynamics of Citation Network for Impact Prediction","date":"2023-04-16","arxiv_id":"2305.01572","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-graph-isomorphism-network-with-weighted","title":"A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition","date":"2022-07-03","arxiv_id":"2207.00940","n_code_links":0,"syntology":null},{"paper":null,"slug":"prognnosis-a-data-driven-model-to-predict-gnn","title":"ProGNNosis: A Data-driven Model to Predict GNN Computation Time Using Graph Metrics","date":"2022-06-16","arxiv_id":"2206.08258","n_code_links":0,"syntology":null},{"paper":"/paper/graph-neural-networks-and-attention-based-cnn","slug":"graph-neural-networks-and-attention-based-cnn","title":"Graph neural networks and attention-based CNN-LSTM for protein classification","date":"2022-04-20","arxiv_id":"2204.09486","n_code_links":1,"syntology":null},{"paper":"/paper/exploiting-neighbor-effect-conv-agnostic-gnns","slug":"exploiting-neighbor-effect-conv-agnostic-gnns","title":"Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily","date":"2022-03-19","arxiv_id":"2203.11200","n_code_links":1,"syntology":null},{"paper":"/paper/domain-adversarial-spatial-temporal-network-a","slug":"domain-adversarial-spatial-temporal-network-a","title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","date":"2022-02-08","arxiv_id":"2202.03630","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-transfer-learning-in-graph","title":"Investigating Transfer Learning in Graph Neural Networks","date":"2022-02-01","arxiv_id":"2202.00740","n_code_links":0,"syntology":null},{"paper":"/paper/decoupling-the-depth-and-scope-of-graph-1","slug":"decoupling-the-depth-and-scope-of-graph-1","title":"Decoupling the Depth and Scope of Graph Neural Networks","date":"2022-01-19","arxiv_id":"2201.07858","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/shaDow_GNN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/architecture-and-operation-adaptive-network","slug":"architecture-and-operation-adaptive-network","title":"Architecture and Operation Adaptive Network for Online Recommendations","date":"2021-08-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/on-graph-neural-network-ensembles-for-large","slug":"on-graph-neural-network-ensembles-for-large","title":"On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction","date":"2021-06-29","arxiv_id":"2106.15529","n_code_links":1,"syntology":null},{"paper":null,"slug":"gabo-graph-augmentations-with-bi-level","title":"GABO: Graph Augmentations with Bi-level Optimization","date":"2021-04-01","arxiv_id":"2104.00722","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-intention-network-for-click-through","title":"Graph Intention Network for Click-through Rate Prediction in Sponsored Search","date":"2021-03-30","arxiv_id":"2103.16164","n_code_links":0,"syntology":null},{"paper":"/paper/structure-enhanced-meta-learning-for-few-shot","slug":"structure-enhanced-meta-learning-for-few-shot","title":"Structure-Enhanced Meta-Learning For Few-Shot Graph Classification","date":"2021-03-05","arxiv_id":"2103.03547","n_code_links":1,"syntology":null},{"paper":null,"slug":"comparisons-of-graph-neural-networks-on","title":"Comparisons of Graph Neural Networks on Cancer Classification Leveraging a Joint of Phenotypic and Genetic Features","date":"2021-01-14","arxiv_id":"2101.05866","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-informative-latent-variables","title":"Identifying Informative Latent Variables Learned by GIN via Mutual Information","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/graph-convolutions-that-can-finally-model","slug":"graph-convolutions-that-can-finally-model","title":"Graph convolutions that can finally model local structure","date":"2020-11-30","arxiv_id":"2011.15069","n_code_links":1,"syntology":null},{"paper":"/paper/single-node-attack-for-fooling-graph-neural-1","slug":"single-node-attack-for-fooling-graph-neural-1","title":"Single-Node Attacks for Fooling Graph Neural Networks","date":"2020-11-06","arxiv_id":"2011.03574","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-independent-noise-condition-for","title":"Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs","date":"2020-10-10","arxiv_id":"2010.04917","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-bottleneck-of-graph-neural-networks","slug":"on-the-bottleneck-of-graph-neural-networks","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","date":"2020-06-09","arxiv_id":"2006.05205","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tech-srl/bottleneck"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-graph-isomorphism-network-for","slug":"understanding-graph-isomorphism-network-for","title":"Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis","date":"2020-01-10","arxiv_id":"2001.03690","n_code_links":1,"syntology":null},{"paper":null,"slug":"approximation-ratios-of-graph-neural-networks","title":"Approximation Ratios of Graph Neural Networks for Combinatorial Problems","date":"2019-05-24","arxiv_id":"1905.10261","n_code_links":0,"syntology":null},{"paper":null,"slug":"avp-physics-informed-data-generation-for","title":"Active Image Synthesis for Efficient Labeling","date":"2019-02-05","arxiv_id":"1902.01522","n_code_links":0,"syntology":null},{"paper":"/paper/how-powerful-are-graph-neural-networks","slug":"how-powerful-are-graph-neural-networks","title":"How Powerful are Graph Neural Networks?","date":"2018-10-01","arxiv_id":"1810.00826","n_code_links":19,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":5,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["weihua916/powerful-gnns"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"papers_shown":43,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":43,"with_a_code_link":25,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":43,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/method/gin/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/gin/papers/ran/1","json":"/method/gin/papers/ran/1.json","rows":5}],"tasks":[{"task":"/task/graph-classification","name":"Graph Classification","papers":10},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":9},{"task":"/task/node-classification","name":"Node Classification","papers":7},{"task":"/task/graph-learning","name":"Graph Learning","papers":4},{"task":"/task/classification-1","name":"Classification","papers":3},{"task":"/task/classification","name":"General Classification","papers":3},{"task":"/task/molecular-property-prediction","name":"Molecular Property Prediction","papers":3},{"task":"/task/property-prediction","name":"Property Prediction","papers":3},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":2},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":2},{"task":"/task/feature-engineering","name":"Feature Engineering","papers":2},{"task":"/task/graph-property-prediction","name":"Graph Property Prediction","papers":2},{"task":"/task/graph-regression","name":"Graph Regression","papers":2},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":2},{"task":"/task/link-prediction","name":"Link Prediction","papers":2},{"task":"/task/prediction","name":"Prediction","papers":2},{"task":"/task/representation-learning","name":"Representation Learning","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2}],"tasks_shown":20,"n_tasks":59,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":2},{"year":"2020","papers":5},{"year":"2021","papers":7},{"year":"2022","papers":7},{"year":"2023","papers":7},{"year":"2024","papers":8},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gin"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=GIN","read_at":"2026-10-05T00:56:53+00:00","query":"GIN","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"General Incompressible-flow Network (GIN)","origin_arxiv_id":"2001.04872"},"resolution":"alias","resolved_name_differs":true,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"1810.00826","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"mentioned_in_github"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2001.04872","citations":137},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'GIN'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2001.04872","page":"/paper/disentanglement-by-nonlinear-ica-with-general","syntology_url":"https://syntology.ai/paper/2001.04872","in_graph_layer":true,"samples":5,"ran":4,"n_ran_checked":4,"n_instrument":0,"unverified":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"about another paper, arXiv:2001.04872: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: mentioned on GitHub). The lookup matched a different name in Syntology's graph, 'General Incompressible-flow Network (GIN)' (resolution: alias); this answer is about that name. About another paper: this answer is about arXiv:2001.04872, while the archive credits arXiv:1810.00826.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"6b866c91ebd5a081abb5073ac9ba65e9d1b3860b5252d936b6269d669137ebcc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}