{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JS3LWUT6IH4J4PIBEGYBOQLEER","short_pith_number":"pith:JS3LWUT6","schema_version":"1.0","canonical_sha256":"4cb6bb527e41f89e3d0121b017416424603c5bf4d53165eb96d799edb56e0cc7","source":{"kind":"arxiv","id":"2402.18875","version":1},"attestation_state":"computed","paper":{"title":"Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hansi Yang, Quanming Yao, Xiaoyi Fu, Zhen Hao Wong","submitted_at":"2024-02-29T05:44:41Z","abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) are a class of deep learning models designed specifically for heterogeneous graphs, which are graphs that contain different types of nodes and edges. This paper investigates the application of curriculum learning techniques to improve the performance and robustness of Heterogeneous Graph Neural Networks (GNNs). To better classify the quality of the data, we design a loss-aware training schedule, named LTS that measures the quality of every nodes of the data and incorporate the training dataset into the model in a progressive manner that increases dif"},"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":"2402.18875","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T05:44:41Z","cross_cats_sorted":[],"title_canon_sha256":"30f64d4b7f13e59994d74a7c4eee42e26d5a201517b55a713f1185cf76a9e3cc","abstract_canon_sha256":"de3886df6e8d5fa994b956cb015c1548e053bd253459867f614139c9726807ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:25.855340Z","signature_b64":"OX6j5rUhO3Cm3/AS0RLKAwCGP0ZqpNXQgxFghft7HAtGMGl/F2mB1YSitDE2mSTyoolOCXvwNIsS4ppkEJJCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cb6bb527e41f89e3d0121b017416424603c5bf4d53165eb96d799edb56e0cc7","last_reissued_at":"2026-07-05T08:17:25.854947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:25.854947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hansi Yang, Quanming Yao, Xiaoyi Fu, Zhen Hao Wong","submitted_at":"2024-02-29T05:44:41Z","abstract_excerpt":"Heterogeneous Graph Neural Networks (HGNNs) are a class of deep learning models designed specifically for heterogeneous graphs, which are graphs that contain different types of nodes and edges. This paper investigates the application of curriculum learning techniques to improve the performance and robustness of Heterogeneous Graph Neural Networks (GNNs). To better classify the quality of the data, we design a loss-aware training schedule, named LTS that measures the quality of every nodes of the data and incorporate the training dataset into the model in a progressive manner that increases dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18875","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/2402.18875/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":"2402.18875","created_at":"2026-07-05T08:17:25.855004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18875v1","created_at":"2026-07-05T08:17:25.855004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18875","created_at":"2026-07-05T08:17:25.855004+00:00"},{"alias_kind":"pith_short_12","alias_value":"JS3LWUT6IH4J","created_at":"2026-07-05T08:17:25.855004+00:00"},{"alias_kind":"pith_short_16","alias_value":"JS3LWUT6IH4J4PIB","created_at":"2026-07-05T08:17:25.855004+00:00"},{"alias_kind":"pith_short_8","alias_value":"JS3LWUT6","created_at":"2026-07-05T08:17:25.855004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20678","citing_title":"Attention-Driven Metapath Encoding in Heterogeneous Graphs","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER","json":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER.json","graph_json":"https://pith.science/api/pith-number/JS3LWUT6IH4J4PIBEGYBOQLEER/graph.json","events_json":"https://pith.science/api/pith-number/JS3LWUT6IH4J4PIBEGYBOQLEER/events.json","paper":"https://pith.science/paper/JS3LWUT6"},"agent_actions":{"view_html":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER","download_json":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER.json","view_paper":"https://pith.science/paper/JS3LWUT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18875&json=true","fetch_graph":"https://pith.science/api/pith-number/JS3LWUT6IH4J4PIBEGYBOQLEER/graph.json","fetch_events":"https://pith.science/api/pith-number/JS3LWUT6IH4J4PIBEGYBOQLEER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER/action/storage_attestation","attest_author":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER/action/author_attestation","sign_citation":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER/action/citation_signature","submit_replication":"https://pith.science/pith/JS3LWUT6IH4J4PIBEGYBOQLEER/action/replication_record"}},"created_at":"2026-07-05T08:17:25.855004+00:00","updated_at":"2026-07-05T08:17:25.855004+00:00"}