{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006161444,0.0002776446,0.0002439435,0.000482038,0.001960184,0.0007294178,0.002380924,0.0002353274,0.000004727555],"category_scores_gemma":[0.0007153618,0.0002881897,0.0001361727,0.001717299,0.0001021464,0.001784052,0.000798357,0.0009525442,0.000008885449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001339858,"about_ca_system_score_gemma":0.0000464586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000653191,"about_ca_topic_score_gemma":0.00001891199,"domain_scores_codex":[0.9979486,0.0001346215,0.000644264,0.0004022261,0.0003925536,0.0004777574],"domain_scores_gemma":[0.9976318,0.0001020434,0.0003123082,0.001573597,0.0002978127,0.00008242339],"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":[0.0009692952,0.001240019,0.007669631,0.003850309,0.001651011,0.00003575386,0.006820999,0.6486871,0.005506036,0.03932261,0.02035996,0.2638873],"study_design_scores_gemma":[0.001113788,0.0000963179,0.004758652,0.0003514618,0.00003813515,0.00001831507,0.0004606862,0.9268342,0.004087216,0.06144337,0.0003822286,0.0004156086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2504091,0.00002272458,0.7454874,0.001973567,0.0006074256,0.0004844144,0.00003090402,0.0008205096,0.0001639796],"genre_scores_gemma":[0.9897972,0.00007120582,0.009880506,0.00005730806,0.00001600042,0.00007944198,0.00007431587,0.000008717101,0.00001525676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7393882,"threshold_uncertainty_score":0.999957,"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."}}