Practical applications employing deep learning must guarantee inference quality. However, we found that the inference quality of state-of-the-art and state-of-the-practice in practical applications has a long tail distribution. In the real world, many tasks have strict requirements for the quality of deep learning inference, such as safety-critical and mission-critical tasks. The fluctuation of inference quality seriously affects its practical applications, and the quality at the tail may lead to severe consequences. State-of-the-art and state-of-the-practice with outstanding inference quality designed and trained under loose constraints still have poor inference quality under constraints with practical application significance. On the one hand, the neural network models must be deployed on complex systems with limited resources. On the other hand, safety-critical and mission-critical tasks need to meet more metric constraints while ensuring high inference quality. We coin a new term, ``tail quality,'' to characterize this essential requirement and challenge. We also propose a new metric, ``X-Critical-Quality,'' to measure the inference quality under certain constraints. This article reveals factors contributing to the failure of using state-of-the-art and state-of-the-practice algorithms and systems in real scenarios. Therefore, we call for establishing innovative methodologies and tools to tackle this enormous challenge.
Previous computation models either have equivalent abilities in representing all computations but fail to provide primitive operators for programming complex algorithms or lack generalized expression ability to represent newly-added computations. This article presents a unified computation model with generalized expression ability and a concise set of primitive operators for programming high-level algorithms. We propose a unified data abstraction -- Tensor of List, and offer a unified computation model based on Tensor of List, which we call the ToL model (in short, ToL). ToL introduces five atomic computations that can represent any elementary computation by finite composition, ensured with strict formal proof. Based on ToL, we design a pure-functional language -- ToLang. ToLang provides a concise set of primitive operators that can be used to program complex big data and AI algorithms. Our evaluations show ToL has generalized expression ability and a built-in performance indicator, born with a strictly defined computation metric -- elementary operation count (EOPs), consistent with FLOPs within a small error range.
Scientific research communities are embracing AI-based solutions to target tractable scientific tasks and improve research workflows. However, the development and evaluation of such solutions are scattered across multiple disciplines. We formalize the problem of scientific AI benchmarking, and propose a system called SAIBench in the hope of unifying the efforts and enabling low-friction on-boarding of new disciplines. The system approaches this goal with SAIL, a domain-specific language to decouple research problems, AI models, ranking criteria, and software/hardware configuration into reusable modules. We show that this approach is flexible and can adapt to problems, AI models, and evaluation methods defined in different perspectives. The project homepage is https://www.computercouncil.org/SAIBench
This paper quantitatively reveals the state-of-the-art and state-of-the-practice AI systems only achieve acceptable performance on the stringent conditions that all categories of subjects are known, which we call closed clinical settings, but fail to work in real-world clinical settings. Compared to the diagnosis task in the closed setting, real-world clinical settings pose severe challenges, and we must treat them differently. We build a clinical AI benchmark named Clinical AIBench to set up real-world clinical settings to facilitate researches. We propose an open, dynamic machine learning framework and develop an AI system named OpenClinicalAI to diagnose diseases in real-world clinical settings. The first versions of Clinical AIBench and OpenClinicalAI target Alzheimer's disease. In the real-world clinical setting, OpenClinicalAI significantly outperforms the state-of-the-art AI system. In addition, OpenClinicalAI develops personalized diagnosis strategies to avoid unnecessary testing and seamlessly collaborates with clinicians. It is promising to be embedded in the current medical systems to improve medical services.
Attention is an effective mechanism to improve the deep model capability. Squeeze-and-Excite (SE) introduces a light-weight attention branch to enhance the network's representational power. The attention branch is gated using the Sigmoid function and multiplied by the feature map's trunk branch. It is too sensitive to coordinate and balance the trunk and attention branches' contributions. To control the attention branch's influence, we propose a new attention method, called Shift-and-Balance (SB). Different from Squeeze-and-Excite, the attention branch is regulated by the learned control factor to control the balance, then added into the feature map's trunk branch. Experiments show that Shift-and-Balance attention significantly improves the accuracy compared to Squeeze-and-Excite when applied in more layers, increasing more size and capacity of a network. Moreover, Shift-and-Balance attention achieves better or close accuracy compared to the state-of-art Dynamic Convolution.
Federated learning (FL) is a new machine learning paradigm, the goal of which is to build a machine learning model based on data sets distributed on multiple devices--so called Isolated Data Island--while keeping their data secure and private. Most existing work manually splits commonly-used public datasets into partitions to simulate real-world Isolated Data Island while failing to capture the intrinsic characteristics of real-world domain data, like medicine, finance or AIoT. To bridge this huge gap, this paper presents and characterizes an Isolated Data Island benchmark suite, named FLBench, for benchmarking federated learning algorithms. FLBench contains three domains: medical, financial and AIoT. By configuring various domains, FLBench is qualified for evaluating the important research aspects of federated learning, and hence become a promising platform for developing novel federated learning algorithms. Finally, FLBench is fully open-sourced and in fast-evolution. We package it as an automated deployment tool. The benchmark suite will be publicly available from http://www.benchcouncil.org/FLBench.
To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN). Different from Batch Normalization (BN), which normalizes the final summation of the weighted inputs, FBN normalizes the intermediate state of the summation. We propose a novel light-weight network based on FBN, called Finet. At training time, the convolutional layer with FBN can be seen as an inverted bottleneck mechanism. FBN can be fused into convolution at inference time. After fusion, Finet uses the standard convolution with equal channel width, thus makes the inference more efficient. On ImageNet classification dataset, Finet achieves the state-of-art performance (65.706% accuracy with 43M FLOPs, and 73.786% accuracy with 303M FLOPs), Moreover, experiments show that Finet is more efficient than other state-of-art light-weight networks.
Due to increasing amounts of data and compute resources, deep learning achieves many successes in various domains. The application of deep learning on the mobile and embedded devices is taken more and more attentions, benchmarking and ranking the AI abilities of mobile and embedded devices becomes an urgent problem to be solved. Considering the model diversity and framework diversity, we propose a benchmark suite, AIoTBench, which focuses on the evaluation of the inference abilities of mobile and embedded devices. AIoTBench covers three typical heavy-weight networks: ResNet50, InceptionV3, DenseNet121, as well as three light-weight networks: SqueezeNet, MobileNetV2, MnasNet. Each network is implemented by three frameworks which are designed for mobile and embedded devices: Tensorflow Lite, Caffe2, Pytorch Mobile. To compare and rank the AI capabilities of the devices, we propose two unified metrics as the AI scores: Valid Images Per Second (VIPS) and Valid FLOPs Per Second (VOPS). Currently, we have compared and ranked 5 mobile devices using our benchmark. This list will be extended and updated soon after.
Real-world application scenarios like modern Internet services consist of diversity of AI and non-AI modules with very long and complex execution paths. Using component or micro AI benchmarks alone can lead to error-prone conclusions. This paper proposes a scenario-distilling AI benchmarking methodology. Instead of using real-world applications, we propose the permutations of essential AI and non-AI tasks as a scenario-distilling benchmark. We consider scenario-distilling benchmarks, component and micro benchmarks as three indispensable parts of a benchmark suite. Together with seventeen industry partners, we identify nine important real-world application scenarios. We design and implement a highly extensible, configurable, and flexible benchmark framework. On the basis of the framework, we propose the guideline for building scenario-distilling benchmarks, and present two Internet service AI ones. The preliminary evaluation shows the advantage of scenario-distilling AI benchmarking against using component or micro AI benchmarks alone. The specifications, source code, testbed, and results are publicly available from the web site \url{http://www.benchcouncil.org/AIBench/index.html}.
The booming successes of machine learning in different domains boost industry-scale deployments of innovative AI algorithms, systems, and architectures, and thus the importance of benchmarking grows. However, the confidential nature of the workloads, the paramount importance of the representativeness and diversity of benchmarks, and the prohibitive cost of training a state-of-the-art model mutually aggravate the AI benchmarking challenges. In this paper, we present a balanced AI benchmarking methodology for meeting the subtly different requirements of different stages in developing a new system/architecture and ranking/purchasing commercial off-the-shelf ones. Performing an exhaustive survey on the most important AI domain-Internet services with seventeen industry partners, we identify and include seventeen representative AI tasks to guarantee the representativeness and diversity of the benchmarks. Meanwhile, for reducing the benchmarking cost, we select a benchmark subset to a minimum-three tasks-according to the criteria: diversity of model complexity, computational cost, and convergence rate, repeatability, and having widely-accepted metrics or not. We contribute by far the most comprehensive AI benchmark suite-AIBench. The evaluations show AIBench outperforms MLPerf in terms of the diversity and representativeness of model complexity, computational cost, convergent rate, computation and memory access patterns, and hotspot functions. With respect to the AIBench full benchmarks, its subset shortens the benchmarking cost by 41%, while maintaining the primary workload characteristics. The specifications, source code, and performance numbers are publicly available from the web site http://www.benchcouncil.org/AIBench/index.html.