{"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/beyond-real-world-benchmark-datasets-an","title":"Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs","arxiv_id":"2206.09144","date":"2022-06-18","proceeding":null,"authors":["Seiji Maekawa","Koki Noda","Yuya Sasaki","Makoto Onizuka"],"abstract":"Graph Neural Networks (GNNs) have achieved great success on a node classification task. Despite the broad interest in developing and evaluating GNNs, they have been assessed with limited benchmark datasets. As a result, the existing evaluation of GNNs lacks fine-grained analysis from various characteristics of graphs. Motivated by this, we conduct extensive experiments with a synthetic graph generator that can generate graphs having controlled characteristics for fine-grained analysis. Our empirical studies clarify the strengths and weaknesses of GNNs from four major characteristics of real-world graphs with class labels of nodes, i.e., 1) class size distributions (balanced vs. imbalanced), 2) edge connection proportions between classes (homophilic vs. heterophilic), 3) attribute values (biased vs. random), and 4) graph sizes (small vs. large). In addition, to foster future research on GNNs, we publicly release our codebase that allows users to evaluate various GNNs with various graphs. We hope this work offers interesting insights for future research.","url_abs":"https://arxiv.org/abs/2206.09144v6","url_pdf":"https://arxiv.org/pdf/2206.09144v6.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":"beyond-real-world-benchmark-datasets-an","repo_url":"https://github.com/seijimaekawa/empirical-study-of-gnns","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.09144","atlas_url":"https://app.syntology.ai/?focus=2206.09144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09144"}},"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/seijimaekawa/empirical-study-of-gnns","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":0,"samples":[{"code_sha256_prefix":"30b3432cea6fd419","entry":"dense2sparseTensor","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30b3432cea6fd419"}},{"code_sha256_prefix":"1188867287351db7","entry":"get_data_dir","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/train_model.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/train_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1188867287351db7"}},{"code_sha256_prefix":"da80a2b9fd449bd2","entry":"index_to_mask","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da80a2b9fd449bd2"}},{"code_sha256_prefix":"ff7d55c8c0dd7dde","entry":"normalize_string","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff7d55c8c0dd7dde"}},{"code_sha256_prefix":"319940b150558f96","entry":"random_planetoid_splits","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"319940b150558f96"}},{"code_sha256_prefix":"623066b29237a22e","entry":"read_file","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/dataset_utils.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/dataset_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"623066b29237a22e"}},{"code_sha256_prefix":"3a4a478be185334b","entry":"swish","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a4a478be185334b"}},{"code_sha256_prefix":"a24b6d4b9d32db82","entry":"resolver","repo":"seijimaekawa/empirical-study-of-gnns","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/seijimaekawa/empirical-study-of-gnns/blob/HEAD/models/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a24b6d4b9d32db82"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}