DenseShift: Towards Accurate and Transferable Low-Bit Shift Network

Deploying deep neural networks on low-resource edge devices is challenging due to their ever-increasing resource requirements. Recent investigations propose multiplication-free neural networks to reduce computation and memory consumption. Shift neural network is one of the most effective tools towards these reductions. However, existing low-bit shift networks are not as accurate as their full precision counterparts and cannot efficiently transfer to a wide range of tasks due to their inherent design flaws. We propose DenseShift network that exploits the following novel designs. First, we demonstrate that the zero-weight values in low-bit shift networks are neither useful to the model capacity nor simplify the model inference. Therefore, we propose to use a zero-free shifting mechanism to simplify inference while increasing the model capacity. Second, we design a new metric to measure the weight freezing issue in training low-bit shift networks, and propose a sign-scale decomposition to improve the training efficiency. Third, we propose the low-variance random initialization strategy to improve the model's performance in transfer learning scenarios. We run extensive experiments on various computer vision and speech tasks. The experimental results show that DenseShift network significantly outperforms existing low-bit multiplication-free networks and can achieve competitive performance to the full-precision counterpart. It also exhibits strong transfer learning performance with no drop in accuracy.

Is Integer Arithmetic Enough for Deep Learning Training?

The ever-increasing computational complexity of deep learning models makes their training and deployment difficult on various cloud and edge platforms. Replacing floating-point arithmetic with low-bit integer arithmetic is a promising approach to save energy, memory footprint, and latency of deep learning models. As such, quantization has attracted the attention of researchers in recent years. However, using integer numbers to form a fully functional integer training pipeline including forward pass, back-propagation, and stochastic gradient descent is not studied in detail. Our empirical and mathematical results reveal that integer arithmetic is enough to train deep learning models. Unlike recent proposals, instead of quantization, we directly switch the number representation of computations. Our novel training method forms a fully integer training pipeline that does not change the trajectory of the loss and accuracy compared to floating-point, nor does it need any special hyper-parameter tuning, distribution adjustment, or gradient clipping. Our experimental results show that our proposed method is effective in a wide variety of tasks such as classification (including vision transformers), object detection, and semantic segmentation.

Rethinking Pareto Frontier for Performance Evaluation of Deep Neural Networks

Recent efforts in deep learning show a considerable advancement in redesigning deep learning models for low-resource and edge devices. The performance optimization of deep learning models are conducted either manually or through automatic architecture search, or a combination of both. The throughput and power consumption of deep learning models strongly depend on the target hardware. We propose to use a \emph{multi-dimensional} Pareto frontier to re-define the efficiency measure using a multi-objective optimization, where other variables such as power consumption, latency, and accuracy play a relative role in defining a dominant model. Furthermore, a random version of the multi-dimensional Pareto frontier is introduced to mitigate the uncertainty of accuracy, latency, and throughput variations of deep learning models in different experimental setups. These two breakthroughs provide an objective benchmarking method for a wide range of deep learning models. We run our novel multi-dimensional stochastic relative efficiency on a wide range of deep image classification models trained ImageNet data. Thank to this new approach we combine competing variables with stochastic nature simultaneously in a single relative efficiency measure. This allows to rank deep models that run efficiently on different computing hardware, and combines inference efficiency with training efficiency objectively.

Demystifying and Generalizing BinaryConnect

BinaryConnect (BC) and its many variations have become the de facto standard for neural network quantization. However, our understanding of the inner workings of BC is still quite limited. We attempt to close this gap in four different aspects: (a) we show that existing quantization algorithms, including post-training quantization, are surprisingly similar to each other; (b) we argue for proximal maps as a natural family of quantizers that is both easy to design and analyze; (c) we refine the observation that BC is a special case of dual averaging, which itself is a special case of the generalized conditional gradient algorithm; (d) consequently, we propose ProxConnect (PC) as a generalization of BC and we prove its convergence properties by exploiting the established connections. We conduct experiments on CIFAR-10 and ImageNet, and verify that PC achieves competitive performance.

Kronecker Decomposition for GPT Compression

GPT is an auto-regressive Transformer-based pre-trained language model which has attracted a lot of attention in the natural language processing (NLP) domain due to its state-of-the-art performance in several downstream tasks. The success of GPT is mostly attributed to its pre-training on huge amount of data and its large number of parameters (from ~100M to billions of parameters). Despite the superior performance of GPT (especially in few-shot or zero-shot setup), this overparameterized nature of GPT can be very prohibitive for deploying this model on devices with limited computational power or memory. This problem can be mitigated using model compression techniques; however, compressing GPT models has not been investigated much in the literature. In this work, we use Kronecker decomposition to compress the linear mappings of the GPT-22 model. Our Kronecker GPT-2 model (KnGPT2) is initialized based on the Kronecker decomposed version of the GPT-2 model and then is undergone a very light pre-training on only a small portion of the training data with intermediate layer knowledge distillation (ILKD). Finally, our KnGPT2 is fine-tuned on down-stream tasks using ILKD as well. We evaluate our model on both language modeling and General Language Understanding Evaluation benchmark tasks and show that with more efficient pre-training and similar number of parameters, our KnGPT2 outperforms the existing DistilGPT2 model significantly.

Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition

Modern Convolutional Neural Network (CNN) architectures, despite their superiority in solving various problems, are generally too large to be deployed on resource constrained edge devices. In this paper, we reduce memory usage and floating-point operations required by convolutional layers in CNNs. We compress these layers by generalizing the Kronecker Product Decomposition to apply to multidimensional tensors, leading to the Generalized Kronecker Product Decomposition(GKPD). Our approach yields a plug-and-play module that can be used as a drop-in replacement for any convolutional layer. Experimental results for image classification on CIFAR-10 and ImageNet datasets using ResNet, MobileNetv2 and SeNet architectures substantiate the effectiveness of our proposed approach. We find that GKPD outperforms state-of-the-art decomposition methods including Tensor-Train and Tensor-Ring as well as other relevant compression methods such as pruning and knowledge distillation.

iRNN: Integer-only Recurrent Neural Network

Recurrent neural networks (RNN) are used in many real-world text and speech applications. They include complex modules such as recurrence, exponential-based activation, gate interaction, unfoldable normalization, bi-directional dependence, and attention. The interaction between these elements prevents running them on integer-only operations without a significant performance drop. Deploying RNNs that include layer normalization and attention on integer-only arithmetic is still an open problem. We present a quantization-aware training method for obtaining a highly accurate integer-only recurrent neural network (iRNN). Our approach supports layer normalization, attention, and an adaptive piecewise linear approximation of activations, to serve a wide range of RNNs on various applications. The proposed method is proven to work on RNN-based language models and automatic speech recognition. Our iRNN maintains similar performance as its full-precision counterpart, their deployment on smartphones improves the runtime performance by $2\times$, and reduces the model size by $4\times$.

KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation

The development of over-parameterized pre-trained language models has made a significant contribution toward the success of natural language processing. While over-parameterization of these models is the key to their generalization power, it makes them unsuitable for deployment on low-capacity devices. We push the limits of state-of-the-art Transformer-based pre-trained language model compression using Kronecker decomposition. We use this decomposition for compression of the embedding layer, all linear mappings in the multi-head attention, and the feed-forward network modules in the Transformer layer. We perform intermediate-layer knowledge distillation using the uncompressed model as the teacher to improve the performance of the compressed model. We present our KroneckerBERT, a compressed version of the BERT_BASE model obtained using this framework. We evaluate the performance of KroneckerBERT on well-known NLP benchmarks and show that for a high compression factor of 19 (5% of the size of the BERT_BASE model), our KroneckerBERT outperforms state-of-the-art compression methods on the GLUE. Our experiments indicate that the proposed model has promising out-of-distribution robustness and is superior to the state-of-the-art compression methods on SQuAD.

$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks

Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy efficient compared to conventional neural networks. However, existing shift networks are sensitive to the weight initialization, and also yield a degraded performance caused by vanishing gradient and weight sign freezing problem. To address these issues, we propose S low-bit re-parameterization, a novel technique for training low-bit shift networks. Our method decomposes a discrete parameter in a sign-sparse-shift 3-fold manner. In this way, it efficiently learns a low-bit network with a weight dynamics similar to full-precision networks and insensitive to weight initialization. Our proposed training method pushes the boundaries of shift neural networks and shows 3-bit shift networks out-performs their full-precision counterparts in terms of top-1 accuracy on ImageNet.

A Twin Neural Model for Uplift

Uplift is a particular case of conditional treatment effect modeling. Such models deal with cause-and-effect inference for a specific factor, such as a marketing intervention or a medical treatment. In practice, these models are built on individual data from randomized clinical trials where the goal is to partition the participants into heterogeneous groups depending on the uplift. Most existing approaches are adaptations of random forests for the uplift case. Several split criteria have been proposed in the literature, all relying on maximizing heterogeneity. However, in practice, these approaches are prone to overfitting. In this work, we bring a new vision to uplift modeling. We propose a new loss function defined by leveraging a connection with the Bayesian interpretation of the relative risk. Our solution is developed for a specific twin neural network architecture allowing to jointly optimize the marginal probabilities of success for treated and control individuals. We show that this model is a generalization of the uplift logistic interaction model. We modify the stochastic gradient descent algorithm to allow for structured sparse solutions. This helps training our uplift models to a great extent. We show our proposed method is competitive with the state-of-the-art in simulation setting and on real data from large scale randomized experiments.