CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization

• Published in: IEEE transaction on neural networks and learning systems Vol. 35; no. 8; pp. 11595 - 11607
• Main Authors: Hu, Wenzheng, Che, Zhengping, Liu, Ning, Li, Mingyang, Tang, Jian, Zhang, Changshui, Wang, Jianqiang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2024
• Subjects: Compression; Computational modeling; Convolutional neural networks; Costs; deep model; Logic gates; Optimization; pruning; Redundancy; subtask; Task analysis; trace ratio
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2023.3262952

Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks. However, most existing pruning approaches are driven by empirical heuristics and rarely consider the joint impact of channels, leading to unguaranteed and suboptimal performance. In this article, we propose a novel channel pruning method via c lass-aware t race r atio o ptimization (CATRO) to reduce the computational burden and accelerate the model inference. Utilizing class information from a few samples, CATRO measures the joint impact of multiple channels by feature space discriminations and consolidates the layerwise impact of preserved channels. By formulating channel pruning as a submodular set function maximization problem, CATRO solves it efficiently via a two-stage greedy iterative optimization procedure. More importantly, we present theoretical justifications on convergence of CATRO and performance of pruned networks. Experimental results demonstrate that CATRO achieves higher accuracy with similar computation cost or lower computation cost with similar accuracy than other state-of-the-art channel pruning algorithms. In addition, because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.