{"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/rethinking-reconstruction-based-graph-level","title":"Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy","arxiv_id":"2410.20366","date":"2024-10-27","proceeding":null,"authors":["Sunwoo Kim","Soo Yong Lee","Fanchen Bu","Shinhwan Kang","Kyungho Kim","Jaemin Yoo","Kijung Shin"],"abstract":"Graph autoencoders (Graph-AEs) learn representations of given graphs by aiming to accurately reconstruct them. A notable application of Graph-AEs is graph-level anomaly detection (GLAD), whose objective is to identify graphs with anomalous topological structures and/or node features compared to the majority of the graph population. Graph-AEs for GLAD regard a graph with a high mean reconstruction error (i.e. mean of errors from all node pairs and/or nodes) as anomalies. Namely, the methods rest on the assumption that they would better reconstruct graphs with similar characteristics to the majority. We, however, report non-trivial counter-examples, a phenomenon we call reconstruction flip, and highlight the limitations of the existing Graph-AE-based GLAD methods. Specifically, we empirically and theoretically investigate when this assumption holds and when it fails. Through our analyses, we further argue that, while the reconstruction errors for a given graph are effective features for GLAD, leveraging the multifaceted summaries of the reconstruction errors, beyond just mean, can further strengthen the features. Thus, we propose a novel and simple GLAD method, named MUSE. The key innovation of MUSE involves taking multifaceted summaries of reconstruction errors as graph features for GLAD. This surprisingly simple method obtains SOTA performance in GLAD, performing best overall among 14 methods across 10 datasets.","url_abs":"https://arxiv.org/abs/2410.20366v1","url_pdf":"https://arxiv.org/pdf/2410.20366v1.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":"rethinking-reconstruction-based-graph-level","repo_url":"https://github.com/kswoo97/GLAD_MUSE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.20366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20366"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/kswoo97/GLAD_MUSE","reach":null}],"summary":{"ran":2,"ran_draft_wrong":4,"ran_fixture":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"community":{"samples":3,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"6b3abe06c8b61a63","entry":"MUSE_representation_learning","repo":"kswoo97/GLAD_MUSE","repo_kind":"official","path":"src.py","file_url":"https://github.com/kswoo97/GLAD_MUSE/blob/HEAD/src.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b3abe06c8b61a63"}},{"code_sha256_prefix":"c25a2af8838a5048","entry":"SubsetSampler","repo":"kswoo97/GLAD_MUSE","repo_kind":"official","path":"src.py","file_url":"https://github.com/kswoo97/GLAD_MUSE/blob/HEAD/src.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c25a2af8838a5048"}},{"code_sha256_prefix":"b22b48bb429101bb","entry":"make_attention_mask","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b22b48bb429101bb"}},{"code_sha256_prefix":"e88526ab8fc3ebc4","entry":"make_attention_mask","repo":"huggingface/open-muse","repo_kind":"community","path":"muse/modeling_transformer.py","file_url":"https://github.com/huggingface/open-muse/blob/HEAD/muse/modeling_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e88526ab8fc3ebc4"}},{"code_sha256_prefix":"1a6c10e37cb97711","entry":"prob_mask_like","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1a6c10e37cb97711"}},{"code_sha256_prefix":"162f6eae613812c6","entry":"prob_mask_like","repo":"huggingface/open-muse","repo_kind":"community","path":"muse/modeling_transformer.py","file_url":"https://github.com/huggingface/open-muse/blob/HEAD/muse/modeling_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"162f6eae613812c6"}},{"code_sha256_prefix":"7daf2f4e6899de97","entry":"uniform","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7daf2f4e6899de97"}},{"code_sha256_prefix":"66e51521e0875290","entry":"uniform","repo":"huggingface/open-muse","repo_kind":"community","path":"muse/modeling_transformer.py","file_url":"https://github.com/huggingface/open-muse/blob/HEAD/muse/modeling_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"66e51521e0875290"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}