{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SP2PNJ4WNSA5HCX3T4LW6FN577","short_pith_number":"pith:SP2PNJ4W","schema_version":"1.0","canonical_sha256":"93f4f6a7966c81d38afb9f176f15bdfff97e722bd625664506c654e288f92a5c","source":{"kind":"arxiv","id":"1905.12265","version":3},"attestation_state":"computed","paper":{"title":"Strategies for Pre-training Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bowen Liu, Joseph Gomes, Jure Leskovec, Marinka Zitnik, Percy Liang, Vijay Pande, Weihua Hu","submitted_at":"2019-05-29T08:11:52Z","abstract_excerpt":"Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training. An effective approach to this challenge is to pre-train a model on related tasks where data is abundant, and then fine-tune it on a downstream task of interest. While pre-training has been effective in many language and vision domains, it remains an open question how to effectively use pre-training on graph datasets. In this paper, we develop a new strategy and self-supervised methods "},"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":"1905.12265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T08:11:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"935dc0621b3417d0ffc10a547959dbb5d1cc60e77e5404073a857c7fdfa39613","abstract_canon_sha256":"7b2fe8f3fb209b643573d3e9164563228a2764e8141bcfd9b29b2d6f98e21bce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:19.298630Z","signature_b64":"kIF3nI6VSXPma0UMntvIcwFCSm/At5VX1LrdNKClBoDQM367DvZ5WMMl9HRllWfm93sIRmenuubkwXzgAGz9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93f4f6a7966c81d38afb9f176f15bdfff97e722bd625664506c654e288f92a5c","last_reissued_at":"2026-07-05T00:42:19.298218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:19.298218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strategies for Pre-training Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bowen Liu, Joseph Gomes, Jure Leskovec, Marinka Zitnik, Percy Liang, Vijay Pande, Weihua Hu","submitted_at":"2019-05-29T08:11:52Z","abstract_excerpt":"Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training. An effective approach to this challenge is to pre-train a model on related tasks where data is abundant, and then fine-tune it on a downstream task of interest. While pre-training has been effective in many language and vision domains, it remains an open question how to effectively use pre-training on graph datasets. In this paper, we develop a new strategy and self-supervised methods "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12265","kind":"arxiv","version":3},"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/1905.12265/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":"1905.12265","created_at":"2026-07-05T00:42:19.298277+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12265v3","created_at":"2026-07-05T00:42:19.298277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12265","created_at":"2026-07-05T00:42:19.298277+00:00"},{"alias_kind":"pith_short_12","alias_value":"SP2PNJ4WNSA5","created_at":"2026-07-05T00:42:19.298277+00:00"},{"alias_kind":"pith_short_16","alias_value":"SP2PNJ4WNSA5HCX3","created_at":"2026-07-05T00:42:19.298277+00:00"},{"alias_kind":"pith_short_8","alias_value":"SP2PNJ4W","created_at":"2026-07-05T00:42:19.298277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06224","citing_title":"Canopy: A Heterograph Foundation Model for Metabolic Engineering","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17667","citing_title":"Handling Feature Heterogeneity with Learnable Graph Patches","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07700","citing_title":"EssentialGIN: a new approach for gene essentiality prediction based on graph isomorphism neural networks","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05693","citing_title":"MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04154","citing_title":"EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24082","citing_title":"Detecting Gravitational-Wave Anisotropies with Simulation-Based Inference","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07598","citing_title":"A Topological Characterization of Graph Neural Networks via Stochastic Block Model Embeddings on the n-Sphere","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31315","citing_title":"Graph Neural Networks Are Not Continuous Across Graph Resolutions","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22597","citing_title":"Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2408.13471","citing_title":"Disentangled Generative Graph Representation Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2410.02082","citing_title":"FARM: Enhancing Molecular Representations with Functional Group Awareness","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18084","citing_title":"Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17656","citing_title":"Pretraining a Foundation Model for Small-Molecule Natural Products","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2504.05454","citing_title":"GraphPINE: Graph Importance Propagation for Interpretable Drug Response Prediction","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16559","citing_title":"Synergistic Benefits of Joint Molecule Generation and Property Prediction","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21600","citing_title":"ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21610","citing_title":"AgForce Enables Antigen-conditioned Generative Antibody Design","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16416","citing_title":"SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21485","citing_title":"EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16088","citing_title":"Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13932","citing_title":"Rethinking Molecular OOD Generalization via Target-Aware Source Selection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12662","citing_title":"scShapeBench: Discovering geometry from high dimensional scRNAseq data","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02549","citing_title":"Financial Anomaly Detection for the Canadian Market","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10985","citing_title":"Structural Interpretations of Protein Language Model Representations via Differentiable Graph Partitioning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10722","citing_title":"On Improving Graph Neural Networks for QSAR by Pre-training on Extended-Connectivity Fingerprints","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577","json":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577.json","graph_json":"https://pith.science/api/pith-number/SP2PNJ4WNSA5HCX3T4LW6FN577/graph.json","events_json":"https://pith.science/api/pith-number/SP2PNJ4WNSA5HCX3T4LW6FN577/events.json","paper":"https://pith.science/paper/SP2PNJ4W"},"agent_actions":{"view_html":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577","download_json":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577.json","view_paper":"https://pith.science/paper/SP2PNJ4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12265&json=true","fetch_graph":"https://pith.science/api/pith-number/SP2PNJ4WNSA5HCX3T4LW6FN577/graph.json","fetch_events":"https://pith.science/api/pith-number/SP2PNJ4WNSA5HCX3T4LW6FN577/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577/action/storage_attestation","attest_author":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577/action/author_attestation","sign_citation":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577/action/citation_signature","submit_replication":"https://pith.science/pith/SP2PNJ4WNSA5HCX3T4LW6FN577/action/replication_record"}},"created_at":"2026-07-05T00:42:19.298277+00:00","updated_at":"2026-07-05T00:42:19.298277+00:00"}