{"id":"W4406949434","doi":"10.1109/tifs.2025.3536612","title":"Protecting Your Attention During Distributed Graph Learning: Efficient Privacy-Preserving Federated Graph Attention Network","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Japan Society for the Promotion of Science; China Scholarship Council","keywords":"Computer science; Graph; Information privacy; Theoretical computer science; Privacy protection; Computer security","routes":{"ca_aff":true,"ca_fund":false,"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":[0.00247405,0.0009153142,0.001106015,0.0009426357,0.001113954,0.001377167,0.002966627,0.001523646,0.002491162],"category_scores_gemma":[0.01198817,0.0004614259,0.0008483083,0.00119331,0.001388176,0.004792185,0.004523761,0.002099723,0.000534554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001930325,"about_ca_system_score_gemma":0.00177315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00387291,"about_ca_topic_score_gemma":0.006102179,"domain_scores_codex":[0.9980166,0.0005884942,0.00007800703,0.000586068,0.0005079359,0.0002229212],"domain_scores_gemma":[0.9954665,0.001814339,0.0003577182,0.001555472,0.0005294781,0.0002765395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005887951,0.0003550267,0.003697192,0.0001888398,0.0001169991,0.0003455457,0.0007000772,0.4298513,0.0156376,0.05600936,0.01027247,0.4822368],"study_design_scores_gemma":[0.00001806805,0.0000575873,0.000308234,0.000006868207,0.00001569819,0.00008766506,0.00004778022,0.9578697,0.004171133,0.03620397,0.001203904,0.000009310452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03505533,0.0002208021,0.9610018,0.0005441639,0.00003762307,0.00009158859,0.0001353615,0.001537317,0.001375956],"genre_scores_gemma":[0.7979078,0.0001951929,0.1965009,0.0005104025,0.00007052269,0.0001673897,0.0005820412,0.0002219403,0.003843863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00387291,"threshold_uncertainty_score":0.01400554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01253725931744548,"score_gpt":0.2381750029075514,"score_spread":0.2256377435901059,"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."}}