Despite the increasing interest in neural architecture search (NAS), the significant computational cost of NAS is a hindrance to researchers. Hence, we propose to reduce the cost of NAS using proxy data, i.e., a representative subset of the target data, without sacrificing search performance. Even though data selection has been used across various fields, our evaluation of existing selection methods for NAS algorithms offered by NAS-Bench-1shot1 reveals that they are not always appropriate for NAS and a new selection method is necessary. By analyzing proxy data constructed using various selection methods through data entropy, we propose a novel proxy data selection method tailored for NAS. To empirically demonstrate the effectiveness, we conduct thorough experiments across diverse datasets, search spaces, and NAS algorithms. Consequently, NAS algorithms with the proposed selection discover architectures that are competitive with those obtained using the entire dataset. It significantly reduces the search cost: executing DARTS with the proposed selection requires only 40 minutes on CIFAR-10 and 7.5 hours on ImageNet with a single GPU. Additionally, when the architecture searched on ImageNet using the proposed selection is inversely transferred to CIFAR-10, a state-of-the-art test error of 2.4\% is yielded. Our code is available at https://github.com/nabk89/NAS-with-Proxy-data.
Key Lab of High Confidence Software Technologies, Peking University（北京大学高可信软件技术重点实验室）；Institute of Computational Social Science, Peking University (Qingdao)（北京大学计算社会科学研究所（青岛））；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Kuaishou Technology（快手科技）；Data Platform, TEG, Tencent Inc.（腾讯科技（深圳）有限公司TEG数据平台）
Designing neural architectures requires immense manual efforts. This has promoted the development of neural architecture search (NAS) to automate the design. While previous NAS methods achieve promising results but run slowly, zero-cost proxies run extremely fast but are less promising. Therefore, it is of great potential to accelerate NAS via those zero-cost proxies. The existing method has two limitations, which are unforeseeable reliability and one-shot usage. To address the limitations, we present ProxyBO, an efficient Bayesian optimization (BO) framework that utilizes the zero-cost proxie…
Due to the recent advances on Neural Architecture Search (NAS), it gains popularity in designing best networks for specific tasks. Although it shows promising results on many benchmarks and competitions, NAS still suffers from its demanding computation cost for searching high dimensional architectural design space, and this problem becomes even worse when we want to use a large-scale dataset. If we can make a reliable data proxy for NAS, the efficiency of NAS approaches increase accordingly. Our basic observation for making a data proxy is that each example in a specific dataset has a differen…
One of the biggest bottlenecks in a machine learning workflow is waiting for models to train. Depending on the available computing resources, it can take days to weeks to train a neural network on a large dataset with many classes such as ImageNet. For researchers experimenting with new algorithmic approaches, this is impractically time consuming and costly. We aim to generate smaller "proxy datasets" where experiments are cheaper to run but results are highly correlated with experimental results on the full dataset. We generate these proxy datasets using by randomly sampling from examples or …
Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. $10^4$ GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet). Differentiable NAS can reduce the cost of GPU hours via a continuous representation of network architecture but suffers from the high GPU memory consumption issue (grow linearly w.r.t. candidate set size). As a result, they need to utilize~\emph{proxy} tasks, such as training on…
Towards Training-free Automatic Proxy Discovery via Large Language Models for Mixed Precision Quantization
School of Computer and Communication Engineering, Northeastern University（东北大学计算机与通信工程学院）；School of Software Engineering, Beijing Jiaotong University（北京交通大学软件工程学院）；School of Software, Northeastern University（东北大学软件学院）
The University of Sydney（悉尼大学）；Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）
Neural Architecture Search (NAS) achieves significant progress in many computer vision tasks. While many methods have been proposed to improve the efficiency of NAS, the search progress is still laborious because training and evaluating plausible architectures over large search space is time-consuming. Assessing network candidates under a proxy (i.e., computationally reduced setting) thus becomes inevitable. In this paper, we observe that most existing proxies exhibit different behaviors in maintaining the rank consistency among network candidates. In particular, some proxies can be more relia…
Neural Architecture Search (NAS) is an open and challenging problem in machine learning. While NAS offers great promise, the prohibitive computational demand of most of the existing NAS methods makes it difficult to directly search the architectures on large-scale tasks. The typical way of conducting large scale NAS is to search for an architectural building block on a small dataset (either using a proxy set from the large dataset or a completely different small scale dataset) and then transfer the block to a larger dataset. Despite a number of recent results that show the promise of transfer …
Fudan University（复旦大学）；Shanghai AI Laboratory（上海人工智能实验室）；Oracle（甲骨文公司）
Neural Architecture Search has attracted increasing attention in recent years. Among them, differential NAS approaches such as DARTS, have gained popularity for the search efficiency. However, they still suffer from three main issues, that are, the weak stability due to the performance collapse, the poor generalization ability of the searched architectures, and the inferior robustness to different kinds of proxies. To solve the stability and generalization problems, a simple-but-effective regularization method, termed as Beta-Decay, is proposed to regularize the DARTS-based NAS searching proce…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University at Buffalo（布法罗大学）；Georgia Institute of Technology（佐治亚理工学院）；Purdue University（普渡大学）
Neural Architecture Search (NAS) has become a de facto approach in the recent trend of AutoML to design deep neural networks (DNNs). Efficient or near-zero-cost NAS proxies are further proposed to address the demanding computational issues of NAS, where each candidate architecture network only requires one iteration of backpropagation. The values obtained from the proxies are considered the predictions of architecture performance on downstream tasks. However, two significant drawbacks hinder the extended usage of Efficient NAS proxies. (1) Efficient proxies are not adaptive to various search s…
University of California, Riverside（加州大学河滨分校）；George Mason University（乔治梅森大学）；University of Notre Dame（圣母大学）
Convolutional neural networks (CNNs) are used in numerous real-world applications such as vision-based autonomous driving and video content analysis. To run CNN inference on various target devices, hardware-aware neural architecture search (NAS) is crucial. A key requirement of efficient hardware-aware NAS is the fast evaluation of inference latencies in order to rank different architectures. While building a latency predictor for each target device has been commonly used in state of the art, this is a very time-consuming process, lacking scalability in the presence of extremely diverse device…
Recently, Neural Architecture Search (NAS) methods have been introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to adapt the given neural architecture to improve performance while maintaining computational costs. However, NAT lacks reproducibility and it requires an additional architecture adaptation process before network weight training. In this paper, we propose proxyless neural architecture adaptation that is reproducible and efficient. Our method can be applied to both supervised learning and self-supervised l…
One-shot NAS method has attracted much interest from the research community due to its remarkable training efficiency and capacity to discover high performance models. However, the search spaces of previous one-shot based works usually relied on hand-craft design and were short for flexibility on the network topology. In this work, we try to enhance the one-shot NAS by exploring high-performing network architectures in our large-scale Topology Augmented Search Space (i.e., over 3.4*10^10 different topological structures). Specifically, the difficulties for architecture searching in such a comp…
Recently, predictor-based algorithms emerged as a promising approach for neural architecture search (NAS). For NAS, we typically have to calculate the validation accuracy of a large number of Deep Neural Networks (DNNs), what is computationally complex. Predictor-based NAS algorithms address this problem. They train a proxy model that can infer the validation accuracy of DNNs directly from their network structure. During optimization, the proxy can be used to narrow down the number of architectures for which the true validation accuracy must be computed, what makes predictor-based algorithms s…
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；School of EIC, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；Horizon Robotics（地平线机器人）
Neural architecture search (NAS) methods have been proposed to release human experts from tedious architecture engineering. However, most current methods are constrained in small-scale search due to the issue of computational resources. Meanwhile, directly applying architectures searched on small datasets to large datasets often bears no performance guarantee. This limitation impedes the wide use of NAS on large-scale tasks. To overcome this obstacle, we propose an elastic architecture transfer mechanism for accelerating large-scale neural architecture search (EAT-NAS). In our implementations,…
Recent advances in Neural Architecture Search (NAS) such as one-shot NAS offer the ability to extract specialized hardware-aware sub-network configurations from a task-specific super-network. While considerable effort has been employed towards improving the first stage, namely, the training of the super-network, the search for derivative high-performing sub-networks is still under-explored. Popular methods decouple the super-network training from the sub-network search and use performance predictors to reduce the computational burden of searching on different hardware platforms. We propose a f…
Southern University of Science and Technology（南方科技大学）；Shanghai Aircraft Design and Research Institute（上海飞机设计研究院）
For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries.Due to the costly stochastic gradient descent (SGD) training of CNNs for performance evaluation, most existing NAS methods are computationally expensive for real-world deployments. To address this issue, we first introduce a new performance estimation metric, named Random-Weight Evaluation (RWE) to quantify the quality of CNNs in a cost-efficient manner. Instead of fully training the enti…
MIT Media Laboratory（麻省理工学院媒体实验室）；Harvard University（哈佛大学）
Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this paper, we show that standard frequentist regression models can predict the final performance of partially trained model configurations using features based on network architectures, hyperparameters, and time-series validation performance data. We empirically show that our performance prediction models are much more effective than prominent Bayesian counterparts, are simpler to implement, and are faster to train. Our mode…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Texas A&M University（德克萨斯农工大学）；Beijing Jiaotong University（北京交通大学）；University of Oregon（俄勒冈大学）；Facebook AI Applied Research（脸书AI应用研究部）；Zhejiang University（浙江大学）
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS has been explosively studied to automate the discovery of top-performer neural networks, but suffers from heavy resource consumption and often incurs search bias due to truncated training or approximations. Recent NAS works start to explore indicators that can predict a network's performance without training. However, they either leveraged limited properties of deep networks, or the benefits of their training-free i…
Zero-Shot Neural Architecture Search with Weighted Response Correlation
School of Internet, Anhui University（安徽大学互联网学院）；Alibaba Group Holding Limited（阿里巴巴集团控股有限公司）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Alibaba International Digital Commerce（阿里巴巴国际数字商业）；Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳高性能数据挖掘重点实验室，深圳先进技术研究所，中国科学院）
SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization
SIGS & Dept. of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系与清华信息科学与技术国家实验室（SIGS））；SIGS, Tsinghua University（清华大学SIGS（清华信息科学与技术国家实验室））；National University of Singapore（新加坡国立大学）；Dept. of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Peng Cheng Laboratory（鹏城实验室）
Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions. However, existing NAS algorithms usually compromise on restricted search space and search on proxy task to meet the achievable computational demands. To allow as wide as possible network architectures and avoid the gap between target and proxy dataset, we propose a Densely Connected NAS (DCNAS) framework, which directly searches the optimal network structures for the multi-scale representations of visual information, over a large-scale target datase…
This paper investigates the intriguing question of whether we can create learning algorithms that automatically generate training data, learning environments, and curricula in order to help AI agents rapidly learn. We show that such algorithms are possible via Generative Teaching Networks (GTNs), a general approach that is, in theory, applicable to supervised, unsupervised, and reinforcement learning, although our experiments only focus on the supervised case. GTNs are deep neural networks that generate data and/or training environments that a learner (e.g. a freshly initialized neural network…
Samsung AI Center, Cambridge（三星剑桥人工智能中心）；University of Cambridge（剑桥大学）
Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the best one. To reduce the computational power and time needed, a proxy task is often used for evaluating each model instead of full training. In this paper, we evaluate conventional reduced-training proxies and quantify how well they preserve ranking between multiple models during search when compared with the rankings produced by final trained accuracy. We propose a series of ze…
Neural Architecture Search (NAS), the process of automating architecture engineering, is an appealing next step to advancing end-to-end Automatic Speech Recognition (ASR), replacing expert-designed networks with learned, task-specific architectures. In contrast to early computational-demanding NAS methods, recent gradient-based NAS methods, e.g., DARTS (Differentiable ARchiTecture Search), SNAS (Stochastic NAS) and ProxylessNAS, significantly improve the NAS efficiency. In this paper, we make two contributions. First, we rigorously develop an efficient NAS method via Straight-Through (ST) grad…
SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Beihang University（北京航空航天大学）；Nanyang Technological University（南洋理工大学）；Shanghai AI Laboratory（上海人工智能实验室）
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand. Existing ISP designs always adopt a fixed architecture, e.g., several sequential modules connected in a rigid order. Such a fixed ISP architecture may be suboptimal for real-world applications, where camera sensors, scenes and tasks are diverse. In this study, we propose a novel Reconfigurable ISP (ReconfigISP) whose architecture and parameters can be automatically tailored to specific data and tasks. In particular, we implement several ISP module…
We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs--by three orders of magnitude--compared to industry-strength physics-based PDE solvers. This paper describes a new architectural approach to this task, accompanied by a thorough experimental evaluation on a publicly available reservoir model. We demonstrate that in a practical setting a speedup of more than 2000X can be achieved with an average sequence error of about 10\% relative to the oil-field simulator. The proxy model is contrasted with a high-quality physics-based acceleration baseli…
As data sets grow in size, the ability of learning methods to find structure in them is increasingly hampered by the time needed to search the large spaces of possibilities and generate a score for each that takes all of the observed data into account. For instance, Bayesian networks, the model chosen in this paper, have a super-exponentially large search space for a fixed number of variables. One possible method to alleviate this problem is to use a proxy, such as a Gaussian Process regressor, in place of the true scoring function, training it on a selection of sampled networks. We prove here…
We propose a one-step constrained (OSC) beam search to accelerate recurrent neural network (RNN) transducer (RNN-T) inference. The original RNN-T beam search has a while-loop leading to speed down of the decoding process. The OSC beam search eliminates this while-loop by vectorizing multiple hypotheses. This vectorization is nontrivial as the expansion of the hypotheses within the original RNN-T beam search can be different from each other. However, we found that the hypotheses expanded only once at each decoding step in most cases; thus, we constrained the maximum expansion number to one, the…
One of the most important AI research questions is to trade off computation versus performance since ``perfect rationality" exists in theory but is impossible to achieve in practice. Recently, Monte-Carlo tree search (MCTS) has attracted considerable attention due to the significant performance improvement in various challenging domains. However, the expensive time cost during search severely restricts its scope for applications. This paper proposes the Virtual MCTS (V-MCTS), a variant of MCTS that spends more search time on harder states and less search time on simpler states adaptively. We g…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；FZI Research Center for Information Technology（FZI信息技术研究中心）
Efficient driving in urban traffic scenarios requires foresight. The observation of other traffic participants and the inference of their possible next actions depending on the own action is considered cooperative prediction and planning. Humans are well equipped with the capability to predict the actions of multiple interacting traffic participants and plan accordingly, without the need to directly communicate with others. Prior work has shown that it is possible to achieve effective cooperative planning without the need for explicit communication. However, the search space for cooperative pl…
In the literature on hyper-parameter tuning, a number of recent solutions rely on low-fidelity observations (e.g., training with sub-sampled datasets) in order to efficiently identify promising configurations to be then tested via high-fidelity observations (e.g., using the full dataset). Among these, HyperBand is arguably one of the most popular solutions, due to its efficiency and theoretically provable robustness. In this work, we introduce HyperJump, a new approach that builds on HyperBand's robust search strategy and complements it with novel model-based risk analysis techniques that acce…
Tree-based models underpin many modern semantic search engines and recommender systems due to their sub-linear inference times. In industrial applications, these models operate at extreme scales, where every bit of performance is critical. Memory constraints at extreme scales also require that models be sparse, hence tree-based models are often back-ended by sparse matrix algebra routines. However, there are currently no sparse matrix techniques specifically designed for the sparsity structure one encounters in tree-based models for extreme multi-label ranking/classification (XMR/XMC) problems…
Korea Advanced Institute of Science and Technology（韩国高等科学技术研究院）；Amazon Alexa AI（亚马逊Alexa人工智能部门）；Microsoft Research（微软研究院）；Samsung Electronics（三星电子）
K-nearest neighbor search is one of the fundamental tasks in various applications and the hierarchical navigable small world (HNSW) has recently drawn attention in large-scale cloud services, as it easily scales up the database while offering fast search. On the other hand, a computational storage device (CSD) that combines programmable logic and storage modules on a single board becomes popular to address the data bandwidth bottleneck of modern computing systems. In this paper, we propose a computational storage platform that can accelerate a large-scale graph-based nearest neighbor search al…
Accelerating ground state search of spatial photonic Ising machines with genetic-simulated annealing hybrid algorithm
Institute for Quantum Sensing and Information Processing（量子传感与信息处理研究所）；State Key Laboratory of Photonics and Communications（光子与通信国家重点实验室）；Global College（全球学院）；Shanghai Research Center for Quantum Sciences（上海量子科学研究中心）；Hefei National Laboratory（合肥国家实验室）；Shanghai Quantum Intelligence Sensing Technology Co., Ltd（上海量子智能感知技术有限公司）
Accelerating deep model training and inference is crucial in practice. Existing deep learning frameworks usually concentrate on optimizing training speed and pay fewer attentions to inference-specific optimizations. Actually, model inference differs from training in terms of computation, e.g. parameters are refreshed each gradient update step during training, but kept invariant during inference. These special characteristics of model inference open new opportunities for its optimization. In this paper, we propose a hardware-aware optimization framework, namely Woodpecker-DL (WPK), to accelerat…
In recent years, the availability of larger amounts of energy data and advanced machine learning algorithms has created a surge in building energy prediction research. However, one of the variables in energy prediction models, occupant behavior, is crucial for prediction performance but hard-to-measure or time-consuming to collect from each building. This study proposes an approach that utilizes the search volume of topics (e.g., education} or Microsoft Excel) on the Google Trends platform as a proxy of occupant behavior and use of buildings. Linear correlations were first examined to explore …
Millimeter wave (mmWave) is a key technology to support high data rate demands for 5G applications. Highly directional transmissions are crucial at these frequencies to compensate for high isotropic pathloss. This reliance on di- rectional beamforming, however, makes the cell discovery (cell search) challenging since both base station (gNB) and user equipment (UE) jointly perform a search over angular space to locate potential beams to initiate communication. In the cell discovery phase, sequential beam sweeping is performed through the angular coverage region in order to transmit synchronizat…
