{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005713086,0.0003409681,0.00045422,0.0007426748,0.0005509596,0.0003180078,0.0006742352,0.000148296,0.0001028103],"category_scores_gemma":[0.00004793463,0.0003299498,0.0002131273,0.0014184,0.0001598861,0.000429927,0.00005818508,0.001010945,0.00001011769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001002338,"about_ca_system_score_gemma":0.00006075631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001061879,"about_ca_topic_score_gemma":0.0004755154,"domain_scores_codex":[0.9975479,0.0002307362,0.0005009724,0.0009397733,0.0003952272,0.000385404],"domain_scores_gemma":[0.9984767,0.0004888093,0.0001540528,0.0006117039,0.0001163149,0.0001524285],"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":[0.00004214971,0.0002020528,0.01869974,0.00007020436,0.001076844,0.00003182554,0.00118374,0.3367691,0.00044332,0.008008111,0.000007694579,0.6334652],"study_design_scores_gemma":[0.0001549554,0.00006226987,0.007475493,0.0001695326,0.000425886,0.00001735393,0.000145414,0.974775,0.0124366,0.003821444,0.0001008732,0.0004152359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01263805,0.0002954046,0.9849814,0.00119453,0.0004649061,0.0001610463,0.00001322394,0.0001393752,0.0001120217],"genre_scores_gemma":[0.980663,0.0002382305,0.01797867,0.0008308917,0.00002585683,0.0000237558,0.000003888266,0.00001190598,0.000223776],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.968025,"threshold_uncertainty_score":0.9999152,"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."}}