We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL). Existing NAS methods typically define different search spaces according to different tasks. In order to adapt to different task combinations (i.e., task sets), we disentangle the GP-MTL networks into single-task backbones (optionally encode the task priors), and a hierarchical and layerwise features sharing/fusing scheme across them. This enables us to design a novel and general task-agnostic search space, which inserts cross-task edges (i.e., feature fusion connections) into fixed single-task network backbones. Moreover, we also propose a novel single-shot gradient-based search algorithm that closes the performance gap between the searched architectures and the final evaluation architecture. This is realized with a minimum entropy regularization on the architecture weights during the search phase, which makes the architecture weights converge to near-discrete values and therefore achieves a single model. As a result, our searched model can be directly used for evaluation without (re-)training from scratch. We perform extensive experiments using different single-task backbones on various task sets, demonstrating the promising performance obtained by exploiting the hierarchical and layerwise features, as well as the desirable generalizability to different i) task sets and ii) single-task backbones. The code of our paper is available at https://github.com/bhpfelix/MTLNAS.
UNC at Chapel Hill（北卡罗来纳大学教堂山分校）；Google Research（谷歌研究院）；X, The Moonshot Factory（X，登月工厂）
In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture Search (NAS) can work in synergy to greatly benefit on-device Dense Predictions (DP). Empirical results reveal that the joint learning of the two paradigms is surprisingly effective at improving DP accuracy, achieving superior performance over both the transfer learning of single-task NAS and prior state-of-the-art approaches in MTL, all with just 1/10th of the …
Recent years have witnessed a surging interest in Neural Architecture Search (NAS). Various algorithms have been proposed to improve the search efficiency and effectiveness of NAS, i.e., to reduce the search cost and improve the generalization performance of the selected architectures, respectively. However, the search efficiency of these algorithms is severely limited by the need for model training during the search process. To overcome this limitation, we propose a novel NAS algorithm called NAS at Initialization (NASI) that exploits the capability of a Neural Tangent Kernel in being able to…
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Nanjing University of Science and Technology（南京理工大学）；Microsoft Research Asia（微软亚洲研究院）
While pre-trained language models (e.g., BERT) have achieved impressive results on different natural language processing tasks, they have large numbers of parameters and suffer from big computational and memory costs, which make them difficult for real-world deployment. Therefore, model compression is necessary to reduce the computation and memory cost of pre-trained models. In this work, we aim to compress BERT and address the following two challenging practical issues: (1) The compression algorithm should be able to output multiple compressed models with different sizes and latencies, in ord…
College of Computer Science, Zhejiang University（浙江大学计算机学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Shanghai Institute for Advanced Study, Zhejiang University（浙江大学上海高等研究院）
As an important and challenging problem, multi-domain learning (MDL) typically seeks for a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network. Usually, existing ways of adapter plugging and structure design are handcrafted and fixed for all domains before model learning, resulting in the learning inflexibility and computational intensiveness. With this motivation, we propose to learn a data-driven adapter plugging strategy with Neural Architecture Search (NAS), which automatically determines where to plug for those adapter modules. Furthe…
Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods tend to be slow, as they require large amounts of GPU computation. This bottleneck is mainly due to the performance estimation strategy, which requires the evaluation of the generated architectures, mainly by training them, to update the sampler method. In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the probl…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Model-agnostic meta-learning (MAML) and its variants have become popular approaches for few-shot learning. However, due to the non-convexity of deep neural nets (DNNs) and the bi-level formulation of MAML, the theoretical properties of MAML with DNNs remain largely unknown. In this paper, we first prove that MAML with over-parameterized DNNs is guaranteed to converge to global optima at a linear rate. Our convergence analysis indicates that MAML with over-parameterized DNNs is equivalent to kernel regression with a novel class of kernels, which we name as Meta Neural Tangent Kernels (MetaNTK).…
Bar-Ilan University（巴伊兰大学）；Nvidia（英伟达）；National University of Singapore（新加坡国立大学）
In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for several tasks. Joint training reduces computation costs and improves data efficiency; however, since the gradients of these different tasks may conflict, training a joint model for MTL often yields lower performance than its corresponding single-task counterparts. A common method for alleviating this issue is to combine per-task gradients into a joint update direction using a particular heuristic. In this paper, we propose viewing the gradients combination step as a bargaining game, where tasks negoti…
Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）；Robert Bosch Center for Data Science and Artificial Intelligence（罗伯特·博世数据科学与人工智能中心）；Microsoft Research, India（微软印度研究院）
Task-agnostic pre-training followed by task-specific fine-tuning is a default approach to train NLU models. Such models need to be deployed on devices across the cloud and the edge with varying resource and accuracy constraints. For a given task, repeating pre-training and fine-tuning across tens of devices is prohibitively expensive. We propose SuperShaper, a task agnostic pre-training approach which simultaneously pre-trains a large number of Transformer models by varying shapes, i.e., by varying the hidden dimensions across layers. This is enabled by a backbone network with linear bottlenec…
Duke University（杜克大学）；Peking University（北京大学）；University of Nevada, Reno（内华达大学雷诺分校）；Tsinghua University（清华大学）；ECE Department, Duke University（杜克大学电气与计算机工程系）；Institute of Computational Linguistics, Peking University（北京大学计算语言学研究所）；CSE Department, University of Nevada, Reno（内华达大学雷诺分校计算机科学与工程系）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
Resource is an important constraint when deploying Deep Neural Networks (DNNs) on mobile and edge devices. Existing works commonly adopt the cell-based search approach, which limits the flexibility of network patterns in learned cell structures. Moreover, due to the topology-agnostic nature of existing works, including both cell-based and node-based approaches, the search process is time consuming and the performance of found architecture may be sub-optimal. To address these problems, we propose AutoShrink, a topology-aware Neural Architecture Search(NAS) for searching efficient building block…
Neural Architecture Search (NAS) is a collection of methods to craft the way neural networks are built. We apply this idea to Federated Learning (FL), wherein predefined neural network models are trained on the client/device data. This approach is not optimal as the model developers can't observe the local data, and hence, are unable to build highly accurate and efficient models. NAS is promising for FL which can search for global and personalized models automatically for the non-IID data. Most NAS methods are computationally expensive and require fine-tuning after the search, making it a two-…
National University of Singapore（新加坡国立大学）；Bytedance Inc.（字节跳动公司）
The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs). However, the weights sampling strategy of WSNet ishandcrafted and fixed which may severely limit the expression ability of the resultedCNNs and weaken its compression ability. In this work, we present a novel auto-sampling method that is applicable to both 1D and 2D CNNs with significantperformance improvement over WSNet. Specifically, our proposed auto-samplingmethod learns the sampling rules end-to-end instead …
Facebook；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, decouples the model training and searching process and achieves remarkable search efficiency and accuracy. Two-stage NAS requires sampling from the search space during training, which directly impacts the accuracy of the final searched models. While uniform sampling has been widely used for its simplicity, it is agnostic of the model performance Pareto front, which is the main focus in the search process, and thus, miss…
We evaluate the robustness of a Neural Architecture Search (NAS) algorithm known as Efficient NAS (ENAS) against data agnostic poisoning attacks on the original search space with carefully designed ineffective operations. We empirically demonstrate how our one shot search space poisoning approach exploits design flaws in the ENAS controller to degrade predictive performance on classification tasks. With just two poisoning operations injected into the search space, we inflate prediction error rates for child networks upto 90% on the CIFAR-10 dataset.
Deep learning has proven to be a highly effective problem-solving tool for object detection and image segmentation across various domains such as healthcare and autonomous driving. At the heart of this performance lies neural architecture design which relies heavily on domain knowledge and prior experience on the researchers' behalf. More recently, this process of finding the most optimal architectures, given an initial search space of possible operations, was automated by Neural Architecture Search (NAS). In this paper, we evaluate the robustness of one such algorithm known as Efficient NAS (…
The Pennsylvania State University（宾夕法尼亚州立大学）；Zhejiang University（浙江大学）
This paper asks the intriguing question: is it possible to exploit neural architecture search (NAS) as a new attack vector to launch previously improbable attacks? Specifically, we present EVAS, a new attack that leverages NAS to find neural architectures with inherent backdoors and exploits such vulnerability using input-aware triggers. Compared with existing attacks, EVAS demonstrates many interesting properties: (i) it does not require polluting training data or perturbing model parameters; (ii) it is agnostic to downstream fine-tuning or even re-training from scratch; (iii) it naturally ev…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Georgia Institute of Technology（佐治亚理工学院）；Purdue University（普渡大学）；University at Buffalo（布法罗大学）
Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated by the downstream tasks, e.g., image classification in computer vision. However, extensive experiments have shown that, prominent neural architectures, such as ResNet in computer vision and LSTM in natural language processing, are generally good at extracting patterns from the input data and perform well on different downstream tasks. In this paper, we attempt to answer two fundamental questions related to NAS. (1) Is it necessary to use the performance of specific downstream tasks to evaluate and search f…
Monash University（莫纳什大学）；University of Technology Sydney（悉尼科技大学）；University of Adelaide（阿德莱德大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）
\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the inner model weights and the outer architecture parameter in a weight-sharing supernet. A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation. While much has been discussed about several potentially fatal factors in DARTS, the architecture gradient, a.k.a. hypergradient, h…
Know-Center GmbH（Know-Center有限公司）；Materials Center Leoben Forschung GmbH（莱奥本材料研究中心有限公司）
In this paper, we frame homogeneous-feature multi-task learning (MTL) as a hierarchical representation learning problem, with one task-agnostic and multiple task-specific latent representations. Drawing inspiration from the information bottleneck principle and assuming an additive independent noise model between the task-agnostic and task-specific latent representations, we limit the information contained in each task-specific representation. It is shown that our resulting representations yield competitive performance for several MTL benchmarks. Furthermore, for certain setups, we show that th…
Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Cleanlab；Seoul National University（首尔国立大学）；HEC Montréal（蒙特利尔高等商学院）；Canada CIFAR AI Chair（加拿大CIFAR人工智能讲席）；Amazon Web Services（亚马逊云科技）
Georgia Institute of Technology（佐治亚理工学院）；Google Research（谷歌研究院）；Ant Financial（蚂蚁金服）
Neural Architecture Search (NAS) has been quite successful in constructing state-of-the-art models on a variety of tasks. Unfortunately, the computational cost can make it difficult to scale. In this paper, we make the first attempt to study Meta Architecture Search which aims at learning a task-agnostic representation that can be used to speed up the process of architecture search on a large number of tasks. We propose the Bayesian Meta Architecture SEarch (BASE) framework which takes advantage of a Bayesian formulation of the architecture search problem to learn over an entire set of tasks s…
Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in applications such as image classification and language modeling. However, these techniques typically ignore device-related objectives such as inference time, memory usage, and power consumption. Optimizing neural architecture for device-related objectives is immensely crucial for deploying deep networks on portable devices with limited computing resources. We propose DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e.g., i…
Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras
Lehigh University（理海大学）；University of Pennsylvania（宾夕法尼亚大学）；University of Missouri（密苏里大学）；Shandong University（山东大学）；University of Hong Kong（香港大学）；South China University of Technology（华南理工大学）；Cedars-Sinai Medical Center（西达赛奈医疗中心）
The fundamental problem in Neural Architecture Search (NAS) is to efficiently find high-performing architectures from a given search space. We propose a simple but powerful method which we call FEAR, for ranking architectures in any search space. FEAR leverages the viewpoint that neural networks are powerful non-linear feature extractors. First, we train different architectures in the search space to the same training or validation error. Then, we compare the usefulness of the features extracted by each architecture. We do so with a quick training keeping most of the architecture frozen. This …
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Beijing Jiaotong University（北京交通大学）；Sun Yat-sen University（中山大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Southern University of Science and Technology（南方科技大学）；Michigan State University（密歇根州立大学）
Consiglio Nazionale delle Ricerche（意大利国家研究委员会）；University of Oulu（奥卢大学）；Centre for Wireless Communications（无线通信中心）
Recent advances in Federated Learning (FL) have paved the way towards the design of novel strategies for solving multiple learning tasks simultaneously, by leveraging cooperation among networked devices. Multi-Task Learning (MTL) exploits relevant commonalities across tasks to improve efficiency compared with traditional transfer learning approaches. By learning multiple tasks jointly, significant reduction in terms of energy footprints can be obtained. This article provides a first look into the energy costs of MTL processes driven by the Model-Agnostic Meta-Learning (MAML) paradigm and imple…
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Freiburg（弗莱堡大学）
The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the application of NAS are large amounts of labeled data and compute resources. This renders its application challenging in few-shot learning scenarios, where many related tasks need to be learned, each with limited amounts of data and compute time. Thus, few-shot learning is typically done with a fixed neural architecture. To improve upon this, we propose MetaNAS, the fi…
University of British Columbia（不列颠哥伦比亚大学）；University of Pennsylvania（宾夕法尼亚大学）
Social media currently provide a window on our lives, making it possible to learn how people from different places, with different backgrounds, ages, and genders use language. In this work we exploit a newly-created Arabic dataset with ground truth age and gender labels to learn these attributes both individually and in a multi-task setting at the sentence level. Our models are based on variations of deep bidirectional neural networks. More specifically, we build models with gated recurrent units and bidirectional encoder representations from transformers (BERT). We show the utility of multi-t…
University of Cambridge（剑桥大学）；Shenzhen Institute of Advanced Technology, CAS（中国科学院深圳先进技术研究院）；Microsoft Research（微软研究院）
Network Architecture Search (NAS) methods have recently gathered much attention. They design networks with better performance and use a much shorter search time compared to traditional manual tuning. Despite their efficiency in model deployments, most NAS algorithms target a single task on a fixed hardware system. However, real-life few-shot learning environments often cover a great number of tasks (T ) and deployments on a wide variety of hardware platforms (H ). The combinatorial search complexity T times H creates a fundamental search efficiency challenge if one naively applies existing NAS…
The University of Hong Kong（香港大学）；Sun Yat-sen University（中山大学）；The Hong Kong University of Science and Technology（香港科技大学）
Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They also lack efficient mechanisms to reuse knowledge when confronting multiple tasks. These challenges preclude their applicability, and motivate our proposal of CATCH, a novel Context-bAsed meTa reinforcement learning (RL) algorithm for transferrable arChitecture searcH. The combination of meta-learning and RL allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces. CATCH utilizes a probabi…
To learn good joint policies for multi-agent collaboration with imperfect information remains a fundamental challenge. While for two-player zero-sum games, coordinate-ascent approaches (optimizing one agent's policy at a time, e.g., self-play) work with guarantees, in multi-agent cooperative setting they often converge to sub-optimal Nash equilibrium. On the other hand, directly modeling joint policy changes in imperfect information game is nontrivial due to complicated interplay of policies (e.g., upstream updates affect downstream state reachability). In this paper, we show global changes of…
