{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QZYS7BZ6GV2LSTIDRRFD2GQZW7","short_pith_number":"pith:QZYS7BZ6","schema_version":"1.0","canonical_sha256":"86712f873e3574b94d038c4a3d1a19b7f0d6a243f0d5c9eb7f23c17ee0130ab8","source":{"kind":"arxiv","id":"2605.15695","version":1},"attestation_state":"computed","paper":{"title":"ParamSpMM: Adaptive and Efficient Sparse Matrix-Matrix Multiplication on GPUs for GNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ParamSpMM adapts SpMM on GPUs to graph inputs via a flexible data structure and ML predictor for better GNN efficiency.","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Guanhua Ye, Hongzheng Li, Lixing Zhang, Shigang Li, Yingxia Shao","submitted_at":"2026-05-15T07:38:04Z","abstract_excerpt":"Fueled by the ability to mine real-world graph data, GNN applications have experienced phenomenal growth. Sparse Matrix-Matrix Multiplication (SpMM) is a critical operator in GNNs. However, existing SpMM designs for GNNs struggle to adapt to diverse input characteristics. In this paper, we first conduct a comprehensive analysis of existing SpMM optimizations, revealing their limitations through statistical and empirical evidence. Based on this analysis, we introduce ParamSpMM, a parametric approach for highly adaptive and efficient SpMM computation in GNNs. It incorporates a new data structure"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15695","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-15T07:38:04Z","cross_cats_sorted":[],"title_canon_sha256":"ae9587f0b25d2e2918d5f5dba1086758c9de9bb56d6deec4e7c4e4c13a0a6623","abstract_canon_sha256":"c9942ec6402e6c8017786a136e67d988352da8e1245359aa6ab5e795e249410e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:12.969028Z","signature_b64":"qrm1PyIOMm6YjyTRiOPnEn4MyhfSIdVVVONQ/OK0LLboT/9saOj+N8GQrPRXyfz3kb2KD4FA9QRNwjSVmrTJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86712f873e3574b94d038c4a3d1a19b7f0d6a243f0d5c9eb7f23c17ee0130ab8","last_reissued_at":"2026-05-20T00:01:12.968184Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:12.968184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParamSpMM: Adaptive and Efficient Sparse Matrix-Matrix Multiplication on GPUs for GNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ParamSpMM adapts SpMM on GPUs to graph inputs via a flexible data structure and ML predictor for better GNN efficiency.","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Guanhua Ye, Hongzheng Li, Lixing Zhang, Shigang Li, Yingxia Shao","submitted_at":"2026-05-15T07:38:04Z","abstract_excerpt":"Fueled by the ability to mine real-world graph data, GNN applications have experienced phenomenal growth. Sparse Matrix-Matrix Multiplication (SpMM) is a critical operator in GNNs. However, existing SpMM designs for GNNs struggle to adapt to diverse input characteristics. In this paper, we first conduct a comprehensive analysis of existing SpMM optimizations, revealing their limitations through statistical and empirical evidence. Based on this analysis, we introduce ParamSpMM, a parametric approach for highly adaptive and efficient SpMM computation in GNNs. It incorporates a new data structure"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our evaluations demonstrate that ParamSpMM outperforms Nvidia cuSPARSE with an average speedup of 1.92x, significantly enhancing GNN training efficiency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The ML-based SpMM-decider can reliably predict optimal configurations from the crafted input features across diverse graph characteristics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ParamSpMM uses a Parameterized Compressed Sparse Row format and an ML-based decider to adapt SpMM optimizations for GNNs, delivering 1.92x average speedup over cuSPARSE.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ParamSpMM adapts SpMM on GPUs to graph inputs via a flexible data structure and ML predictor for better GNN efficiency.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1ef72aa7f8cfcdcb524961bc97319c0ecb18915187d17475352c995600ee0205"},"source":{"id":"2605.15695","kind":"arxiv","version":1},"verdict":{"id":"491632c6-e661-44e5-b607-0fadba193968","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T19:32:01.448336Z","strongest_claim":"Our evaluations demonstrate that ParamSpMM outperforms Nvidia cuSPARSE with an average speedup of 1.92x, significantly enhancing GNN training efficiency.","one_line_summary":"ParamSpMM uses a Parameterized Compressed Sparse Row format and an ML-based decider to adapt SpMM optimizations for GNNs, delivering 1.92x average speedup over cuSPARSE.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The ML-based SpMM-decider can reliably predict optimal configurations from the crafted input features across diverse graph characteristics.","pith_extraction_headline":"ParamSpMM adapts SpMM on GPUs to graph inputs via a flexible data structure and ML predictor for better GNN efficiency."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15695/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T20:01:19.221162Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:41:03.222476Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:29.218344Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.038578Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"330779e39c764c3bd12423d104a466ca4e27f623312535f180a4da5bad3531f0"},"references":{"count":32,"sample":[{"doi":"","year":2016,"title":"Arai, J., Shiokawa, H., Yamamuro, T., Onizuka, M., Iwamura, S.: Rabbit order: Just-in-time parallel reordering for fast graph analysis. In: (IPDPS). pp. 22–31 (2016)","work_id":"a8461479-56bf-4291-890a-ad2880deca74","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Bader, D.A., Meyerhenke, H., Sanders, P., Wagner, D.: 10th dimacs implementa- tion challenge-graph partitioning and graph clustering (2011)","work_id":"8d88f590-5041-4ca3-a655-03354b5de463","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"Waschington University in St","work_id":"a8c415f1-dac3-4b00-96b1-bbfed3ba3b6b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Dai, G., Huang, G., Yang, S., Yu, Z., Zhang, H., Ding, Y., Xie, Y., Yang, H., Wang, Y.: Heuristic adaptability to input dynamics for spmm on gpus. p. 595–600. DAC ’22 (2022)","work_id":"fe2bd51e-5ac6-4c29-9fdc-79800ea0f10e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Fan, R., Wang, W., Chu, X.: Fast sparse gpu kernels for accelerated training of graph neural networks. In: (IPDPS). pp. 501–511 (2023)","work_id":"5b6017c0-6221-409d-984a-750aa5c96c8c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"0ed6b87ff91dd5047cf9386db7b26c4bfaa3c0afa27b98073bb0ef30de88dd6f","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"25666ce2ca02b5688b2a440549a4caf793bf62101f96a3f6ee3ec7976492b6aa"},"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":"2605.15695","created_at":"2026-05-20T00:01:12.968312+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15695v1","created_at":"2026-05-20T00:01:12.968312+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15695","created_at":"2026-05-20T00:01:12.968312+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZYS7BZ6GV2L","created_at":"2026-05-20T00:01:12.968312+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZYS7BZ6GV2LSTID","created_at":"2026-05-20T00:01:12.968312+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZYS7BZ6","created_at":"2026-05-20T00:01:12.968312+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7","json":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7.json","graph_json":"https://pith.science/api/pith-number/QZYS7BZ6GV2LSTIDRRFD2GQZW7/graph.json","events_json":"https://pith.science/api/pith-number/QZYS7BZ6GV2LSTIDRRFD2GQZW7/events.json","paper":"https://pith.science/paper/QZYS7BZ6"},"agent_actions":{"view_html":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7","download_json":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7.json","view_paper":"https://pith.science/paper/QZYS7BZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15695&json=true","fetch_graph":"https://pith.science/api/pith-number/QZYS7BZ6GV2LSTIDRRFD2GQZW7/graph.json","fetch_events":"https://pith.science/api/pith-number/QZYS7BZ6GV2LSTIDRRFD2GQZW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7/action/storage_attestation","attest_author":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7/action/author_attestation","sign_citation":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7/action/citation_signature","submit_replication":"https://pith.science/pith/QZYS7BZ6GV2LSTIDRRFD2GQZW7/action/replication_record"}},"created_at":"2026-05-20T00:01:12.968312+00:00","updated_at":"2026-05-20T00:01:12.968312+00:00"}