{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N4FSLJQRPZLB3U4Q5WV3PTHY7R","short_pith_number":"pith:N4FSLJQR","schema_version":"1.0","canonical_sha256":"6f0b25a6117e561dd390edabb7ccf8fc42f85c0bd0fac952d7f84c8826bbc6fa","source":{"kind":"arxiv","id":"2406.03464","version":1},"attestation_state":"computed","paper":{"title":"Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Luo, Hanqing Lu, Haoyu Han, Hui Liu, Jiliang Tang, Juanhui Li, Wei Huang, Xianfeng Tang","submitted_at":"2024-06-05T17:12:38Z","abstract_excerpt":"Graph Neural Networks (GNNs) have proven to be highly effective for node classification tasks across diverse graph structural patterns. Traditionally, GNNs employ a uniform global filter, typically a low-pass filter for homophilic graphs and a high-pass filter for heterophilic graphs. However, real-world graphs often exhibit a complex mix of homophilic and heterophilic patterns, rendering a single global filter approach suboptimal. In this work, we theoretically demonstrate that a global filter optimized for one pattern can adversely affect performance on nodes with differing patterns. To addr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.03464","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T17:12:38Z","cross_cats_sorted":[],"title_canon_sha256":"9528e23bc835aa1588045600f9da324bb39940eb203006c94bba8e3eb0c3bbcc","abstract_canon_sha256":"02a28293dd65d7e2248f5514f0d9fd45d687c3b729caf19edc61bff62ca278af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:57.385333Z","signature_b64":"T4VfaOgKSSDKw3WNxHX1K9scrPNKFnQUWJQp6fgbYrYOENTuYz++zfd13fVYx7EhpsaiBBcX3oCWYTkKrIMIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f0b25a6117e561dd390edabb7ccf8fc42f85c0bd0fac952d7f84c8826bbc6fa","last_reissued_at":"2026-07-05T08:27:57.384804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:57.384804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen Luo, Hanqing Lu, Haoyu Han, Hui Liu, Jiliang Tang, Juanhui Li, Wei Huang, Xianfeng Tang","submitted_at":"2024-06-05T17:12:38Z","abstract_excerpt":"Graph Neural Networks (GNNs) have proven to be highly effective for node classification tasks across diverse graph structural patterns. Traditionally, GNNs employ a uniform global filter, typically a low-pass filter for homophilic graphs and a high-pass filter for heterophilic graphs. However, real-world graphs often exhibit a complex mix of homophilic and heterophilic patterns, rendering a single global filter approach suboptimal. In this work, we theoretically demonstrate that a global filter optimized for one pattern can adversely affect performance on nodes with differing patterns. To addr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03464","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.03464/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.03464","created_at":"2026-07-05T08:27:57.384868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03464v1","created_at":"2026-07-05T08:27:57.384868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03464","created_at":"2026-07-05T08:27:57.384868+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4FSLJQRPZLB","created_at":"2026-07-05T08:27:57.384868+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4FSLJQRPZLB3U4Q","created_at":"2026-07-05T08:27:57.384868+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4FSLJQR","created_at":"2026-07-05T08:27:57.384868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01660","citing_title":"Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25662","citing_title":"Closed-Form Node Classification with Exact Graph Unlearning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11473","citing_title":"Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R","json":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R.json","graph_json":"https://pith.science/api/pith-number/N4FSLJQRPZLB3U4Q5WV3PTHY7R/graph.json","events_json":"https://pith.science/api/pith-number/N4FSLJQRPZLB3U4Q5WV3PTHY7R/events.json","paper":"https://pith.science/paper/N4FSLJQR"},"agent_actions":{"view_html":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R","download_json":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R.json","view_paper":"https://pith.science/paper/N4FSLJQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03464&json=true","fetch_graph":"https://pith.science/api/pith-number/N4FSLJQRPZLB3U4Q5WV3PTHY7R/graph.json","fetch_events":"https://pith.science/api/pith-number/N4FSLJQRPZLB3U4Q5WV3PTHY7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R/action/storage_attestation","attest_author":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R/action/author_attestation","sign_citation":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R/action/citation_signature","submit_replication":"https://pith.science/pith/N4FSLJQRPZLB3U4Q5WV3PTHY7R/action/replication_record"}},"created_at":"2026-07-05T08:27:57.384868+00:00","updated_at":"2026-07-05T08:27:57.384868+00:00"}