DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
Deep neural network (DNN) model compression for efficient on-device inference is becoming increasingly important to reduce memory requirements and keep user data on-device. To this end, we propose a novel differentiable k-means clustering layer (DKM) and its application to train-time weight clustering-based DNN model compression. DKM casts k-means clustering as an attention problem and enables joint optimization of the parameters and clustering centroids. Unlike prior works that rely on additional regularizers and parameters, DKM-based compression keeps the original loss function and model architecture fixed. We evaluated DKM-based compression on various DNN models for computer vision and natural language processing (NLP) tasks. Our results demonstrate that DMK delivers superior compression and accuracy trade-off on ImageNet1k and GLUE benchmarks. For example, DKM-based compression can offer 74.5 model size (29.4x model compression factor). For MobileNet-v1, which is a challenging DNN to compress, DKM delivers 62.8 0.74 MB model size (22.4x model compression factor). This result is 6.8 top-1 accuracy and 33 state-of-the-art DNN compression algorithms. Additionally, DKM enables compression of DistilBERT model by 11.8x with minimal (1.1 GLUE NLP benchmarks.
READ FULL TEXT