It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher

Model quantization is considered as a promising method to greatly reduce the resource requirements of deep neural networks. To deal with the performance drop induced by quantization errors, a popular method is to use training data to fine-tune quantized networks. In real-world environments, however, such a method is frequently infeasible because training data is unavailable due to security, privacy, or confidentiality concerns. Zero-shot quantization addresses such problems, usually by taking information from the weights of a full-precision teacher network to compensate the performance drop of the quantized networks. In this paper, we first analyze the loss surface of state-of-the-art zero-shot quantization techniques and provide several findings. In contrast to usual knowledge distillation problems, zero-shot quantization often suffers from 1) the difficulty of optimizing multiple loss terms together, and 2) the poor generalization capability due to the use of synthetic samples. Furthermore, we observe that many weights fail to cross the rounding threshold during training the quantized networks even when it is necessary to do so for better performance. Based on the observations, we propose AIT, a simple yet powerful technique for zero-shot quantization, which addresses the aforementioned two problems in the following way: AIT i) uses a KL distance loss only without a cross-entropy loss, and ii) manipulates gradients to guarantee that a certain portion of weights are properly updated after crossing the rounding thresholds. Experiments show that AIT outperforms the performance of many existing methods by a great margin, taking over the overall state-of-the-art position in the field.

Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usually requires access to the original training data to maintain the accuracy of the full-precision models, which is often infeasible in real-world scenarios for security and privacy issues. A popular approach to perform quantization without access to the original data is to use synthetically generated samples, based on batch-normalization statistics or adversarial learning. However, the drawback of such approaches is that they primarily rely on random noise input to the generator to attain diversity of the synthetic samples. We find that this is often insufficient to capture the distribution of the original data, especially around the decision boundaries. To this end, we propose Qimera, a method that uses superposed latent embeddings to generate synthetic boundary supporting samples. For the superposed embeddings to better reflect the original distribution, we also propose using an additional disentanglement mapping layer and extracting information from the full-precision model. The experimental results show that Qimera achieves state-of-the-art performances for various settings on data-free quantization. Code is available at https://github.com/iamkanghyunchoi/qimera.

An Attention Module for Convolutional Neural Networks

Attention mechanism has been regarded as an advanced technique to capture long-range feature interactions and to boost the representation capability for convolutional neural networks. However, we found two ignored problems in current attentional activations-based models: the approximation problem and the insufficient capacity problem of the attention maps. To solve the two problems together, we initially propose an attention module for convolutional neural networks by developing an AW-convolution, where the shape of attention maps matches that of the weights rather than the activations. Our proposed attention module is a complementary method to previous attention-based schemes, such as those that apply the attention mechanism to explore the relationship between channel-wise and spatial features. Experiments on several datasets for image classification and object detection tasks show the effectiveness of our proposed attention module. In particular, our proposed attention module achieves 1.00% Top-1 accuracy improvement on ImageNet classification over a ResNet101 baseline and 0.63 COCO-style Average Precision improvement on the COCO object detection on top of a Faster R-CNN baseline with the backbone of ResNet101-FPN. When integrating with the previous attentional activations-based models, our proposed attention module can further increase their Top-1 accuracy on ImageNet classification by up to 0.57% and COCO-style Average Precision on the COCO object detection by up to 0.45. Code and pre-trained models will be publicly available.

AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression

Data-free compression raises a new challenge because the original training dataset for a pre-trained model to be compressed is not available due to privacy or transmission issues. Thus, a common approach is to compute a reconstructed training dataset before compression. The current reconstruction methods compute the reconstructed training dataset with a generator by exploiting information from the pre-trained model. However, current reconstruction methods focus on extracting more information from the pre-trained model but do not leverage network engineering. This work is the first to consider network engineering as an approach to design the reconstruction method. Specifically, we propose the AutoReCon method, which is a neural architecture search-based reconstruction method. In the proposed AutoReCon method, the generator architecture is designed automatically given the pre-trained model for reconstruction. Experimental results show that using generators discovered by the AutoRecon method always improve the performance of data-free compression.

GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent

In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training. As one of processing-in-memory techniques that could be realized in the near future, we propose an incremental, simple architectural design that does not invade the existing memory protocol. Extending DDR4 SDRAM to utilize bank-group parallelism makes our operation designs in processing-in-memory (PIM) module efficient in terms of hardware cost and performance. Our experimental results show that the proposed architecture can improve the performance of DNN training and greatly reduce memory bandwidth requirement while posing only a minimal amount of overhead to the protocol and DRAM area.

Deep Composer Classification Using Symbolic Representation

In this study, we train deep neural networks to classify composer on a symbolic domain. The model takes a two-channel two-dimensional input, i.e., onset and note activations of time-pitch representation, which is converted from MIDI recordings and performs a single-label classification. On the experiments conducted on MAESTRO dataset, we report an F1 value of 0.8333 for the classification of 13~classical composers.

DANCE: Differentiable Accelerator/Network Co-Exploration

To cope with the ever-increasing computational demand of the DNN execution, recent neural architecture search (NAS) algorithms consider hardware cost metrics into account, such as GPU latency. To further pursue a fast, efficient execution, DNN-specialized hardware accelerators are being designed for multiple purposes, which far-exceeds the efficiency of the GPUs. However, those hardware-related metrics have been proven to exhibit non-linear relationships with the network architectures. Therefore it became a chicken-and-egg problem to optimize the network against the accelerator, or to optimize the accelerator against the network. In such circumstances, this work presents DANCE, a differentiable approach towards the co-exploration of the hardware accelerator and network architecture design. At the heart of DANCE is a differentiable evaluator network. By modeling the hardware evaluation software with a neural network, the relation between the accelerator architecture and the hardware metrics becomes differentiable, allowing the search to be performed with backpropagation. Compared to the naive existing approaches, our method performs co-exploration in a significantly shorter time, while achieving superior accuracy and hardware cost metrics.

SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks

Binary Convolutional Neural Networks (BCNNs) can significantly improve the efficiency of Deep Convolutional Neural Networks (DCNNs) for their deployment on resource-constrained platforms, such as mobile and embedded systems. However, the accuracy degradation of BCNNs is still considerable compared with their full precision counterpart, impeding their practical deployment. Because of the inevitable binarization error in the forward propagation and gradient mismatch problem in the backward propagation, it is nontrivial to train BCNNs to achieve satisfactory accuracy. To ease the difficulty of training, the shortcut-based BCNNs, such as residual connection-based Bi-real ResNet and dense connection-based BinaryDenseNet, introduce additional shortcuts in addition to the shortcuts already present in their full precision counterparts. Furthermore, fractal architectures have been also been used to improve the training process of full-precision DCNNs since the fractal structure triggers effects akin to deep supervision and lateral student-teacher information flow. Inspired by the shortcuts and fractal architectures, we propose two Shortcut-based Fractal Architectures (SoFAr) specifically designed for BCNNs: 1. residual connection-based fractal architectures for binary ResNet, and 2. dense connection-based fractal architectures for binary DenseNet. Our proposed SoFAr combines the adoption of shortcuts and the fractal architectures in one unified model, which is helpful in the training of BCNNs. Results show that our proposed SoFAr achieves better accuracy compared with shortcut-based BCNNs. Specifically, the Top-1 accuracy of our proposed RF-c4d8 ResNet37(41) and DRF-c2d2 DenseNet51(53) on ImageNet outperforms Bi-real ResNet18(64) and BinaryDenseNet51(32) by 3.29% and 1.41%, respectively, with the same computational complexity overhead.

MAPS: Multi-agent Reinforcement Learning-based Portfolio Management System

Generating an investment strategy using advanced deep learning methods in stock markets has recently been a topic of interest. Most existing deep learning methods focus on proposing an optimal model or network architecture by maximizing return. However, these models often fail to consider and adapt to the continuously changing market conditions. In this paper, we propose the Multi-Agent reinforcement learning-based Portfolio management System (MAPS). MAPS is a cooperative system in which each agent is an independent "investor" creating its own portfolio. In the training procedure, each agent is guided to act as diversely as possible while maximizing its own return with a carefully designed loss function. As a result, MAPS as a system ends up with a diversified portfolio. Experiment results with 12 years of US market data show that MAPS outperforms most of the baselines in terms of Sharpe ratio. Furthermore, our results show that adding more agents to our system would allow us to get a higher Sharpe ratio by lowering risk with a more diversified portfolio.