{"id":"W4414230387","doi":"10.1109/tpami.2025.3610113","title":"ACLI: A CNN Pruning Framework Leveraging Adjacent Convolutional Layer Interdependence and $\\gamma$γ-Weakly Submodularity","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Benchmark (surveying); Submodular set function; Convolutional neural network; Metric (unit); Reduction (mathematics); Heuristic; Layer (electronics)","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":[0.001987162,0.001908161,0.001423918,0.001411379,0.0006897318,0.001293151,0.003121799,0.001504778,0.002205697],"category_scores_gemma":[0.004634841,0.0006049561,0.0009760211,0.001017526,0.001120605,0.001850009,0.002292728,0.00266925,0.0009897028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001467505,"about_ca_system_score_gemma":0.002732292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00537437,"about_ca_topic_score_gemma":0.008961207,"domain_scores_codex":[0.9988127,0.0002029194,0.0000560877,0.0002110588,0.0005656397,0.0001515764],"domain_scores_gemma":[0.9985566,0.0005340172,0.0001937597,0.0002879864,0.0003278977,0.00009964455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002168864,0.000188222,0.001950038,0.0002735913,0.0001510947,0.0003601477,0.0001493815,0.456957,0.02219006,0.04792202,0.01820507,0.4514365],"study_design_scores_gemma":[0.00001344187,0.00005515724,0.0002436778,0.00002127236,0.00002559757,0.0001273463,0.00001297214,0.9812516,0.004719453,0.01057055,0.002945495,0.00001340551],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009846209,0.0006377587,0.985185,0.0002190636,0.00005476282,0.00008253615,0.0001021825,0.001099176,0.002773271],"genre_scores_gemma":[0.3646543,0.001252887,0.6195425,0.0009980444,0.0002716543,0.0004280868,0.001434701,0.0007848396,0.01063305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00537437,"threshold_uncertainty_score":0.01068616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02280750812612199,"score_gpt":0.2887793482567814,"score_spread":0.2659718401306594,"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."}}