Investigating Learning in Deep Neural Networks using Layer-Wise Weight Change
University of Nebraska（内布拉斯加大学）；University of Nebraska-Lincoln（内布拉斯加大学林肯分校）；Georgia Institute of Technology（佐治亚理工学院）；Ford R&A（福特研究与创新中心）；German University in Cairo（开罗德国大学）
Ayush Manish Agrawal, Atharva Tendle, Harshvardhan Sikka, Sahib Singh, Amr Kayid
Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. We investigate learning in Deep Convolutional Neural Networks (CNNs) by measuring the relative weight change of layers while training. Several interesting trends emerge in a variety of CNN architectures across various computer vision classification tasks, including the overall increase in relative weight change of later layers as compared to earlier ones.
Zhejiang University（浙江大学）；Columbia University（哥伦比亚大学）；University of Rochester（罗切斯特大学）
Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans. However, their most significant drawback is the lack of interpretability, which makes them less attractive in many real-world applications. When relating to the moral problem or the environmental factors that are uncertain such as crime judgment, financial analysis, and medical diagnosis, it is essential to mine the evidence for the model's prediction (interpret model knowledge) to convince humans. Thus, investigating how to inte…
Ningxia University（宁夏大学）；Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence co-founded by Ningxia Municipality and Ministry of Education（宁夏大数据与人工智能省部共建协同创新中心）
Existing differentiable channel pruning methods often attach scaling factors or masks behind channels to prune filters with less importance, and implicitly assume uniform contribution of input samples to filter importance. Specifically, the effects of instance complexity on pruning performance are not yet fully investigated in static network pruning. In this paper, we propose a simple yet effective differentiable network pruning method CWP based on instance complexity weighted filter importance scores. We define instance complexity related weight for each instance by giving higher weights to h…
Northeastern University（东北大学）；University College London（伦敦大学学院）
There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP). To better mimic the brain, training a network $\textit{one layer at a time}$ with only a "single forward pass" has been proposed as an alternative to bypass BP; we refer to these networks as "layer-wise" networks. We continue the work on layer-wise networks by answering two outstanding questions. First, $\textit{do they have a closed-form solution?}$ Second, $\textit{how do we know when to stop adding more layers?}$ This work proves that the kernel Mean Embedding is t…
In importance sampling (IS)-based reinforcement learning algorithms such as Proximal Policy Optimization (PPO), IS weights are typically clipped to avoid large variance in learning. However, policy update from clipped statistics induces large bias in tasks with high action dimensions, and bias from clipping makes it difficult to reuse old samples with large IS weights. In this paper, we consider PPO, a representative on-policy algorithm, and propose its improvement by dimension-wise IS weight clipping which separately clips the IS weight of each action dimension to avoid large bias and adaptiv…
Second-order information has proven to be very effective in determining the redundancy of neural network weights and activations. Recent paper proposes to use Hessian traces of weights and activations for mixed-precision quantization and achieves state-of-the-art results. However, prior works only focus on selecting bits for each layer while the redundancy of different channels within a layer also differ a lot. This is mainly because the complexity of determining bits for each channel is too high for original methods. Here, we introduce Channel-wise Hessian Aware trace-Weighted Quantization (C…
University of Bologna（博洛尼亚大学）；Politecnico di Torino（都灵理工大学）
Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precision quantization, i.e., the use of different bit-widths for different portions of the network, has been shown to provide excellent efficiency gains with limited accuracy drops, especially with optimized bit-width assignments determined by automated Neural Architecture Search (NAS) tools. State-of-the-art mixed-precision works layer-wise, i.e., it uses different bit-widths for the weights and activations tensors of ea…
Weight-Informed Self-Explaining Clustering for Mixed-Type Tabular Data
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）智能科学与工程学院）
We introduce an algorithm where the individual bits representing the weights of a neural network are learned. This method allows training weights with integer values on arbitrary bit-depths and naturally uncovers sparse networks, without additional constraints or regularization techniques. We show better results than the standard training technique with fully connected networks and similar performance as compared to standard training for convolutional and residual networks. By training bits in a selective manner we found that the biggest contribution to achieving high accuracy is given by the …
Classic algebraic reconstruction technology (ART) for computed tomography requires pre-determined weights of the voxels for projecting pixel values. However, such weight cannot be accurately obtained due to the limitation of the physical understanding and computation resources. In this study, we propose a semi-case-wise learning-based method named Weight Encode Reconstruction Network (WERNet) to tackle the issues mentioned above. The model is trained in a self-supervised manner without the label of a voxel set. It contains two branches, including the voxel weight encoder and the voxel attentio…
As a deep learning model typically contains millions of trainable weights, there has been a growing demand for a more efficient network structure with reduced storage space and improved run-time efficiency. Pruning is one of the most popular network compression techniques. In this paper, we propose a novel unstructured pruning pipeline, Attention-based Simultaneous sparse structure and Weight Learning (ASWL). Unlike traditional channel-wise or weight-wise attention mechanism, ASWL proposed an efficient algorithm to calculate the pruning ratio through layer-wise attention for each layer, and bo…
Network quantization is one of the most hardware friendly techniques to enable the deployment of convolutional neural networks (CNNs) on low-power mobile devices. Recent network quantization techniques quantize each weight kernel in a convolutional layer independently for higher inference accuracy, since the weight kernels in a layer exhibit different variances and hence have different amounts of redundancy. The quantization bitwidth or bit number (QBN) directly decides the inference accuracy, latency, energy and hardware overhead. To effectively reduce the redundancy and accelerate CNN infere…
There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP). To better mimic the brain, training a network \textit{one layer at a time} with only a "single forward pass" has been proposed as an alternative to bypass BP; we refer to these networks as "layer-wise" networks. We continue the work on layer-wise networks by answering two outstanding questions. First, $\textit{do they have a closed-form solution?}$ Second, $\textit{how do we know when to stop adding more layers?}$ This work proves that the Kernel Mean Embedding is the…
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation, and language modeling, it performs on par or better than well tuned SGD with momentum and Adam or AdamW. Additionally, NovoGrad (1) is robust to the choice of learning rate and weight initialization, (2) works well in a large batch setting, and (3) has two times smaller memory footprint than Adam.
Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
Huazhong University of Science and Technology（华中科技大学）；Shenzhen Technology University（深圳技术大学）；City University of Hong Kong（香港城市大学）；Shenzhen University（深圳大学）
George Mason University（乔治梅森大学）；Michigan State University（密歇根州立大学）；Northeastern University（东北大学）
This work proposes a novel Deep Neural Network (DNN) quantization framework, namely RMSMP, with a Row-wise Mixed-Scheme and Multi-Precision approach. Specifically, this is the first effort to assign mixed quantization schemes and multiple precisions within layers -- among rows of the DNN weight matrix, for simplified operations in hardware inference, while preserving accuracy. Furthermore, this paper makes a different observation from the prior work that the quantization error does not necessarily exhibit the layer-wise sensitivity, and actually can be mitigated as long as a certain portion of…
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Sydney（悉尼大学）
Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or filters without data, e.g., pruning and decomposition. In contrast, we study this problem from a different perspective by respecting the difference between data. An instance-wise feature pruning is developed by identifying informative features for different instances. Specifically, by investigating a feature decay regularization, we expect intermediate feature…
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization
University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Macau（澳门大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）
Neural networks have achieved state of the art performance across a wide variety of machine learning tasks, often with large and computation-heavy models. Inducing sparseness as a way to reduce the memory and computation footprint of these models has seen significant research attention in recent years. In this paper, we present a new method for \emph{dynamic sparseness}, whereby part of the computations are omitted dynamically, based on the input. For efficiency, we combined the idea of dynamic sparseness with block-wise matrix-vector multiplications. In contrast to static sparseness, which pe…
AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；Peng Cheng Laboratory（鹏城实验室）；University of Chinese Academy of Sciences（中国科学院大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Shenzhen University of Advanced Technology（深圳大学）；University of Oxford（牛津大学）；University of Surrey（萨里大学）
SenseTime Research（商汤科技研究院）；Beihang University（北京航空航天大学）；University of Sydney（悉尼大学）
The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search is the evaluation process for a particular augmentation policy, which is utilized to return reward and usually runs thousands of times. A plain evaluation process, which includes full model training and validation, would be time-consuming. To achieve efficiency, many choose to sacrifice evaluation reliability for speed. In this paper, we dive into the dynamics of augmented training of the model. This inspires us to de…
Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
Department of Electrical and Computer Engineering, Sungkyunkwan University（电气与计算机工程系，全北大学）；Department of Electrical and Computer Engineering, Duke University（电气与计算机工程系，杜克大学）；Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST)（金 Jaechul人工智能研究生院，韩国科学技术院（KAIST））
Ping An Property & Casualty Insurance（平安财产保险股份有限公司）；Beijing University of Posts and Telecommunications（北京邮电大学）
Graph Neural Networks (GNNs) have attracted considerable attention and have emerged as a new promising paradigm to process graph-structured data. GNNs are usually stacked to multiple layers and the node representations in each layer are computed through propagating and aggregating the neighboring node features with respect to the graph. By stacking to multiple layers, GNNs are able to capture the long-range dependencies among the data on the graph and thus bring performance improvements. To train a GNN with multiple layers effectively, some normalization techniques (e.g., node-wise normalizati…
Post-training, layer-wise quantization is preferable because it is free from retraining and is hardware-friendly. Nevertheless, accuracy degradation has occurred when a neural network model has a big difference of per-out-channel weight ranges. In particular, the MobileNet family has a tragedy drop in top-1 accuracy from 70.60% ~ 71.87% to 0.1% on the ImageNet dataset after 8-bit weight quantization. To mitigate this significant accuracy reduction, we propose a new weight equalizing shift scaler, i.e. rescaling the weight range per channel by a 4-bit binary shift, prior to a layer-wise quantiz…
Finetuning can be used to tackle domain-specific tasks by transferring knowledge. Previous studies on finetuning focused on adapting only the weights of a task-specific classifier or re-optimizing all layers of the pre-trained model using the new task data. The first type of methods cannot mitigate the mismatch between a pre-trained model and the new task data, and the second type of methods easily cause over-fitting when processing tasks with limited data. To explore the effectiveness of fine-tuning, we propose a novel block-wise optimization mechanism, which adapts the weights of a group of …
Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)（东南大学新一代人工智能技术及交叉应用重点实验室）
Quantization is an essential step in the efficient deployment of deep learning models and as such is an increasingly popular research topic. An important practical aspect that is not addressed in the current literature is how to analyze and fix fail cases where the use of quantization results in excessive degradation. In this paper, we present a simple analytic framework that breaks down overall degradation to its per layer contributions. We analyze many common networks and observe that a layer's contribution is determined by both intrinsic (local) factors - the distribution of the layer's wei…
Key Lab of Intelligent Information Processing of Chinese Academy of Sciences（中国科学院智能信息处理重点实验室）；Zhejiang University（浙江大学）；Computer Center of Peking University（北京大学计算中心）；Peng Cheng Laboratory（鹏城实验室）
The proposed pruning strategy offers merits over weight-based pruning techniques: (1) it avoids irregular memory access since representations and matrices can be squeezed into their smaller but dense counterparts, leading to greater speedup; (2) in a manner of top-down pruning, the proposed method operates from a more global perspective based on training signals in the top layer, and prunes each layer by propagating the effect of global signals through layers, leading to better performances at the same sparsity level. Extensive experiments show that at the same sparsity level, the proposed str…
We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machine (LPOM). LPOM is block multi-convex in all layer-wise weights and activations. This allows us to use block coordinate descent to update the layer-wise weights and activations in parallel. Most notably, we only use the mapping of the activation function itself, rather than its de…
Neural network pruning is an important step in design process of efficient neural networks for edge devices with limited computational power. Pruning is a form of knowledge transfer from the weights of the original network to a smaller target subnetwork. We propose a new method for compute-constrained structured channel-wise pruning of convolutional neural networks. The method iteratively fine-tunes the network, while gradually tapering the computation resources available to the pruned network via a holonomic constraint in the method of Lagrangian multipliers framework. An explicit and adaptiv…
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
Dartmouth College（达特茅斯学院）；Nanjing University（南京大学）；National Center for Applied Mathematics（国家应用数学中心）；Calculation Consulting（计算咨询公司）；University of California at Berkeley（加州大学伯克利分校）；International Computer Science Institute（国际计算机科学研究所）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
Pennsylvania State University（宾夕法尼亚州立大学）；IBM Research - Almaden（IBM阿尔马登研究中心）
Federated Learning (FL) is a paradigm for jointly training machine learning algorithms in a decentralized manner which allows for parties to communicate with an aggregator to create and train a model, without exposing the underlying raw data distribution of the local parties involved in the training process. Most research in FL has been focused on Neural Network-based approaches, however Tree-Based methods, such as XGBoost, have been underexplored in Federated Learning due to the challenges in overcoming the iterative and additive characteristics of the algorithm. Decision tree-based models, i…
