{"id":"W4416701904","doi":"10.1016/j.inffus.2025.103998","title":"One model connects all graphs: Towards training one unified model for multi-domain graph pre-training using adaptive vector quantization","year":2025,"lang":"en","type":"article","venue":"Information Fusion","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Central China Normal University; China Postdoctoral Science Foundation; Natural Science Foundation of Hubei Province; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Codebook; Vector quantization; Graph; Quantization (signal processing); Linde–Buzo–Gray algorithm; Unified Model; Graph rewriting","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001015418,0.000874429,0.001209026,0.0007065392,0.0003726883,0.001025954,0.002248871,0.001644883,0.00200117],"category_scores_gemma":[0.003575312,0.0005517362,0.0009634753,0.00101629,0.0009246983,0.002631339,0.001695112,0.003263,0.0008049081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008373859,"about_ca_system_score_gemma":0.0009720974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007976851,"about_ca_topic_score_gemma":0.01232045,"domain_scores_codex":[0.9994729,0.0001425674,0.00002384111,0.0002038755,0.00009766943,0.00005911456],"domain_scores_gemma":[0.999012,0.000400181,0.00007685555,0.0002382765,0.0002078897,0.00006483679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001331954,0.0001167665,0.0007544821,0.0001049777,0.00008946533,0.00005303498,0.0001213537,0.7425629,0.004935734,0.0228212,0.004676385,0.2236305],"study_design_scores_gemma":[0.000002581788,0.00001261046,0.00005890885,0.000005756495,0.000005851537,0.000005658376,0.000007054505,0.9919086,0.0003803817,0.007377243,0.0002320654,0.00000319124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01052081,0.0002218138,0.9875498,0.0002267242,0.00004837173,0.00002590424,0.0001000915,0.0006766151,0.0006299094],"genre_scores_gemma":[0.5725406,0.0004765975,0.4205123,0.0005455377,0.00009269033,0.0001678146,0.001026923,0.000396878,0.00424063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007976851,"threshold_uncertainty_score":0.01586086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1471263550498886,"score_gpt":0.3221147255786672,"score_spread":0.1749883705287786,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}