A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks
원문 초록
Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight initialization methods. To be specific, general initialization methods, such as Xavier or Kaiming initialization, usually fail to generate appropriate weights for TCNNs. Meanwhile, although there are ad-hoc approaches for specific architectures (e.g., Tensor Ring Nets), they are not applicable to TCNNs with other tensor decomposition methods (e.g., CP or Tucker decomposition). To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs. Specifically, we first present the Reproducing Transformation to convert the backward process in TCNNs to an equivalent convolution process. Then, based on the convolution operators in the forward and backward processes, we build a unified paradigm to control the variance of features and gradients in TCNNs. Thus, we can derive fan-in and fan-out initialization for various TCNNs. We demonstrate that our paradigm can stabilize the training of TCNNs, leading to faster convergence and better results.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Revisit CP Tensor Decomposition: Statistical Optimality and Fast Convergence
D-Tracker: Modeling Interest Diffusion in Social Activity Tensor Data Streams
Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
Guaranteed Multidimensional Time Series Prediction via Deterministic Tensor Completion Theory
토론
이 논문과 연결된 포럼 글이 아직 없습니다.