{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6DK6VFSAV33OBTNINYZRO4IYIL","short_pith_number":"pith:6DK6VFSA","schema_version":"1.0","canonical_sha256":"f0d5ea9640aef6e0cda86e3317711842c17cf8ec297fb985111664cb71d3cb38","source":{"kind":"arxiv","id":"2009.03509","version":5},"attestation_state":"computed","paper":{"title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hui Zhong, Shikun Feng, Wenjin Wang, Yunsheng Shi, Yu Sun, Zhengjie Huang","submitted_at":"2020-09-08T04:04:04Z","abstract_excerpt":"Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results. However, there is still no effective way to directly combine these two kinds of algorithms. To address this issue, we propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time. First, "},"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":"2009.03509","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-08T04:04:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e35d66861df7a91f4f7a02fc56fcf80ab7c2e63c47cdaf156daa92f928dcb41d","abstract_canon_sha256":"adf8d0679f4e38dbe072d118f224c26806e51e8ff588e2f898cd37a0c1a1c2f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:04.898072Z","signature_b64":"aF4S282/rKguko2PmKoDFIOdEqS15QKVPCKB5/lta/Gr0/uFCvmMfbH7C+V+I+278Kst8w8mih3gtF0AFrcPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d5ea9640aef6e0cda86e3317711842c17cf8ec297fb985111664cb71d3cb38","last_reissued_at":"2026-07-05T02:39:04.897445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:04.897445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hui Zhong, Shikun Feng, Wenjin Wang, Yunsheng Shi, Yu Sun, Zhengjie Huang","submitted_at":"2020-09-08T04:04:04Z","abstract_excerpt":"Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results. However, there is still no effective way to directly combine these two kinds of algorithms. To address this issue, we propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time. First, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.03509","kind":"arxiv","version":5},"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/2009.03509/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":"2009.03509","created_at":"2026-07-05T02:39:04.897505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.03509v5","created_at":"2026-07-05T02:39:04.897505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.03509","created_at":"2026-07-05T02:39:04.897505+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DK6VFSAV33O","created_at":"2026-07-05T02:39:04.897505+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DK6VFSAV33OBTNI","created_at":"2026-07-05T02:39:04.897505+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DK6VFSA","created_at":"2026-07-05T02:39:04.897505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20390","citing_title":"Geometry-Aware Superpixel Graph Transformer with Metadata for Skin Lesion Classification","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31500","citing_title":"On Efficient Scaling of GNNs via IO-Aware Layers Implementations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31371","citing_title":"Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00716","citing_title":"Graph Transfer Learning via Shared Latent Geometry: Theory and Applications","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23241","citing_title":"RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2501.17549","citing_title":"Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00558","citing_title":"Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21435","citing_title":"Gaussian Sheaf Neural Networks","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19589","citing_title":"Physics-Informed Graph Neural Network Surrogates for Turbulent Nanoparticle Dispersion in Dental Clinical Environments","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20170","citing_title":"KoRe: Compact Knowledge Representations for Large Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2105.14491","citing_title":"How Attentive are Graph Attention Networks?","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25599","citing_title":"PLMGH: What Matters in PLM-GNN Hybrids for Code Classification and Vulnerability Detection","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL","json":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL.json","graph_json":"https://pith.science/api/pith-number/6DK6VFSAV33OBTNINYZRO4IYIL/graph.json","events_json":"https://pith.science/api/pith-number/6DK6VFSAV33OBTNINYZRO4IYIL/events.json","paper":"https://pith.science/paper/6DK6VFSA"},"agent_actions":{"view_html":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL","download_json":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL.json","view_paper":"https://pith.science/paper/6DK6VFSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.03509&json=true","fetch_graph":"https://pith.science/api/pith-number/6DK6VFSAV33OBTNINYZRO4IYIL/graph.json","fetch_events":"https://pith.science/api/pith-number/6DK6VFSAV33OBTNINYZRO4IYIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL/action/storage_attestation","attest_author":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL/action/author_attestation","sign_citation":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL/action/citation_signature","submit_replication":"https://pith.science/pith/6DK6VFSAV33OBTNINYZRO4IYIL/action/replication_record"}},"created_at":"2026-07-05T02:39:04.897505+00:00","updated_at":"2026-07-05T02:39:04.897505+00:00"}