{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPPLQN27TQGU6OVGJY4B3SUJ6D","short_pith_number":"pith:KPPLQN27","schema_version":"1.0","canonical_sha256":"53deb8375f9c0d4f3aa64e381dca89f0e9abe7f96ca3309888810cdaa0566a76","source":{"kind":"arxiv","id":"2404.06114","version":1},"attestation_state":"computed","paper":{"title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Feng Liang, Haifeng Lu, Victor C. M. Leung, Xiping Hu, Yanyi Guo, Zhen Zhang","submitted_at":"2024-04-09T08:35:04Z","abstract_excerpt":"With the rapid growth in the volume of data sets, models, and devices in the domain of deep learning, there is increasing attention on large-scale distributed deep learning. In contrast to traditional distributed deep learning, the large-scale scenario poses new challenges that include fault tolerance, scalability of algorithms and infrastructures, and heterogeneity in data sets, models, and resources. Due to intensive synchronization of models and sharing of data across GPUs and computing nodes during distributed training and inference processes, communication efficiency becomes the bottlenec"},"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":"2404.06114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2024-04-09T08:35:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9c5f2037d006056e37becc1bd20343f1b8e2d7f4153573001aea9e77a03a1e8e","abstract_canon_sha256":"0a0dd590e12c0a7394ae1c65303861cba9bb3d137749267b2ebb65ee7122d3a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:04.320972Z","signature_b64":"jS04TA07drUBr95ylf7YC+VMPDqehucv/XVztHVz0TQ8T23gPIt+y/Og4jsgVNsyo5rML9bF9x8uTXou6ZuMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53deb8375f9c0d4f3aa64e381dca89f0e9abe7f96ca3309888810cdaa0566a76","last_reissued_at":"2026-07-05T08:06:04.320470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:04.320470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Feng Liang, Haifeng Lu, Victor C. M. Leung, Xiping Hu, Yanyi Guo, Zhen Zhang","submitted_at":"2024-04-09T08:35:04Z","abstract_excerpt":"With the rapid growth in the volume of data sets, models, and devices in the domain of deep learning, there is increasing attention on large-scale distributed deep learning. In contrast to traditional distributed deep learning, the large-scale scenario poses new challenges that include fault tolerance, scalability of algorithms and infrastructures, and heterogeneity in data sets, models, and resources. Due to intensive synchronization of models and sharing of data across GPUs and computing nodes during distributed training and inference processes, communication efficiency becomes the bottlenec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06114","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/2404.06114/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":"2404.06114","created_at":"2026-07-05T08:06:04.320532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06114v1","created_at":"2026-07-05T08:06:04.320532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06114","created_at":"2026-07-05T08:06:04.320532+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPPLQN27TQGU","created_at":"2026-07-05T08:06:04.320532+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPPLQN27TQGU6OVG","created_at":"2026-07-05T08:06:04.320532+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPPLQN27","created_at":"2026-07-05T08:06:04.320532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12963","citing_title":"ScaleAcross: Designing Multi-Data-Center Infrastructure for Geo-Distributed AI Training","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13434","citing_title":"Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12396","citing_title":"NCCLZ: Compression-Enabled GPU Collectives with Decoupled Quantization and Entropy Coding","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D","json":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D.json","graph_json":"https://pith.science/api/pith-number/KPPLQN27TQGU6OVGJY4B3SUJ6D/graph.json","events_json":"https://pith.science/api/pith-number/KPPLQN27TQGU6OVGJY4B3SUJ6D/events.json","paper":"https://pith.science/paper/KPPLQN27"},"agent_actions":{"view_html":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D","download_json":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D.json","view_paper":"https://pith.science/paper/KPPLQN27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06114&json=true","fetch_graph":"https://pith.science/api/pith-number/KPPLQN27TQGU6OVGJY4B3SUJ6D/graph.json","fetch_events":"https://pith.science/api/pith-number/KPPLQN27TQGU6OVGJY4B3SUJ6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D/action/storage_attestation","attest_author":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D/action/author_attestation","sign_citation":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D/action/citation_signature","submit_replication":"https://pith.science/pith/KPPLQN27TQGU6OVGJY4B3SUJ6D/action/replication_record"}},"created_at":"2026-07-05T08:06:04.320532+00:00","updated_at":"2026-07-05T08:06:04.320532+00:00"}