检索结果-内蒙古大学图书馆

Griffin: Fast Transactional database Index with Hash and B+-Tree

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Nakazono, Sho Bessho, Yutaro Kawashima, Hideyuki Nakamori, Tatsuhiro Computer and Data Science Laboratories NTT Tokyo Japan Faculty of Environment and Information Studies Keio University Kanagawa Japan

Index access is one of the dominant performance factors in transactional database systems. Many systems use a B+tree or one of its variants to handle point and range operations. This access pattern has room for performance improvement. Firstly, point operations can potentially be processed in O(1) with a hash table. Secondly, to ensure serializability of transactions, range operations incur overhead from phantom avoidance techniques that involve additional processing or synchronization, such as an extra traversal of the B+-tree. To address these issues, we propose a hybrid index architecture, Griffin. For point operations, Griffin has a hash table that provides access paths in O(1) time, along with a B+-tree. For phantom avoidance, Griffin employs a precision locking method, which does not involve additional traversal of the B+-tree. Despite its hybrid architecture, Griffin transparently provides linearizable operations and an interface of a single database index. We built a Griffin index combining a hash table and BwTree. Compared to a baseline index that is composed of a BwTree only, it achieves up to 3.1x higher throughput in a point operation dominant workload, and up to 5.4x higher throughput in a range operation dominant workload. © 2024, CC BY.

关键词： database systems

Type-Based Verification of Connectivity Constraints in Lattice Surgery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wakizaka, Ryo Suzuki, Yasunari Igarashi, Atsushi Graduate School of Informatics Kyoto University Japan NTT Computer and Data Science Laboratories Musashino180-8585 Japan

Fault-tolerant quantum computation using lattice surgery can be abstracted as operations on graphs, wherein each logical qubit corresponds to a vertex of the graph, and multi-qubit measurements are accomplished by connecting the vertices with paths between them. Operations attempting to connect vertices without a valid path will result in abnormal termination. As the permissible paths may evolve during execution, it is necessary to statically verify that the execution of a quantum program can be completed. This paper introduces a type-based method to statically verify that well-typed programs can be executed without encountering halts induced by surgery operations. Alongside, we present QLS, a first-order quantum programming language to formalize the execution model of surgery operations. Furthermore, we provide a type checking algorithm by reducing the type checking problem to the offline dynamic connectivity problem. © 2024, CC BY.

关键词： Qubits

LEARNING ROBUST CONVOLUTIONAL NEURAL NETWORKS WITH RELEVANT FEATURE FOCUSING VIA EXPLANATIONS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Adachi, Kazuki Yamaguchi, Shin'ya Computer and Data Science Laboratories NTT Corporation Japan

Existing image recognition techniques based on convolutional neural networks (CNNs) basically assume that the training and test datasets are sampled from i.i.d distributions. However, this assumption is easily broken in the real world because of the distribution shift that occurs when the co-occurrence relations between objects and backgrounds in input images change. Under this type of distribution shift, CNNs learn to focus on features that are not task-relevant, such as backgrounds from the training data, and degrade their accuracy on the test data. To tackle this problem, we propose relevant feature focusing (ReFF). ReFF detects task-relevant features and regularizes CNNs via explanation outputs (e.g., Grad-CAM). Since ReFF is composed of post-hoc explanation modules, it can be easily applied to off-the-shelf CNNs. Furthermore, ReFF requires no additional inference cost at test time because it is only used for regularization while training. We demonstrate that CNNs trained with ReFF focus on features relevant to the target task and that ReFF improves the test-time accuracy. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

Sharing knowledge for meta-learning with feature descriptions 22

学校读者我要写书评

暂无评论

Sharing knowledge for meta-learning with feature description...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Tomoharu Iwata Atsutoshi Kumagai NTT Communication Science Laboratories Kyoto Japan NTT Computer and Data Science Laboratories Tokyo Japan

ISBN: (纸本)9781713871088

Language is an important tool for humans to share knowledge. We propose a meta-learning method that shares knowledge across supervised learning tasks using feature descriptions written in natural language, which have not been used in the existing meta-learning methods. The proposed method improves the predictive performance on unseen tasks with a limited number of labeled data by meta-learning from various tasks. With the feature descriptions, we can find relationships across tasks even when their feature spaces are different. The feature descriptions are encoded using a language model pretrained with a large corpus, which enables us to incorporate human knowledge stored in the corpus into meta-learning. In our experiments, we demonstrate that the proposed method achieves better predictive performance than the existing meta-learning methods using a wide variety of real-world datasets provided by the statistical office of the EU and Japan.

关键词：

Towards Better Online Communication for Future Software Development in Industry

学校读者我要写书评

暂无评论

Towards Better Online Communication for Future Software Deve...

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Masanari Kondo Shinobu Saito Yukako Iimura Eunjong Choi Osamu Mizuno Yasutaka Kamei Naoyasu Ubayashi Kyushu University Japan NTT Computer and Data Science Laboratories Japan Kyoto Institute of Technology Japan

COVID-19 has transformed face-to-face software development into distributed development (e. g., remote work). While the company authors belong to studies microtask programming, an open source software (OSS) -like development, as a solution to employ distributed development, a prior study reports a challenge: online communication in microtask programming takes longer; such lengthy communication discourages developers and affects their completion of assigned tasks. OSS, however, is successfully developed using online communication, such as issues. Hence, we have a question: how does OSS address the online communication challenge? In this experience report, we answer this question based on an empirical study on OSS communication. We found that (1) OSS prefers burst communication similar to face-to-face development, and (2) attracting developers’ attention may be a possible solution. Based on the findings, we discuss the direction of future studies to achieve better online communication in microtask programming in the company. The main contributions of this report are (1) to empirically reveal the actual communication times in OSS and (2) to show how an empirical approach helps industrial collaborators.

关键词：

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chijiwa, Daiki Yamaguchi, Shin'ya Kumagai, Atsutoshi Ida, Yasutoshi NTT Computer and Data Science Laboratories NTT Corporation Japan Kyoto University Japan

Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized NNs can easily overfit to such small dataset. Previous work (e.g. MAML by Finn et al. 2017) tackles this challenge by meta-learning, which learns how to learn from a few data by using various tasks. On the other hand, one conventional approach to avoid overfitting is restricting hypothesis spaces by endowing sparse NN structures like convolution layers in computer vision. However, although such manually-designed sparse structures are sample-efficient for sufficiently large datasets, they are still insufficient for few-shot learning. Then the following questions naturally arise: (1) Can we find sparse structures effective for few-shot learning by meta-learning? (2) What benefits will it bring in terms of meta-generalization? In this work, we propose a novel meta-learning approach, called Meta-ticket, to find optimal sparse subnetworks for few-shot learning within randomly initialized NNs. We empirically validated that Meta-ticket successfully discover sparse subnetworks that can learn specialized features for each given task. Due to this task-wise adaptation ability, Meta-ticket achieves superior meta-generalization compared to MAML-based methods especially with large NNs. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

Effects of local minima and bifurcation delay on combinatorial optimization with continuous variables

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sato, Shintaro NTT Computer and Data Science Laboratories NTT Corporation Musashino180-8585 Japan

Combinatorial optimization problems can be mapped onto Ising models, and their ground state is generally difficult to find. A lot of heuristics for these problems have been proposed, and one promising approach is to use continuous variables. In recent years, one such algorithm has been implemented by using parametric oscillators known as coherent Ising machines. Although these algorithms have been confirmed to have high performance through many experiments, unlike other familiar algorithms such as simulated annealing, their computational ability has not been fully investigated. In this paper, we propose a simple heuristic based on continuous variables whose static and dynamical properties are easy to investigate. Through the analyses of the proposed algorithm, we find that many local minima in the early stage of the optimization and bifurcation delay reduce its performance in a certain class of Ising models. Copyright © 2022, The Authors. All rights reserved.

关键词： Combinatorial optimization

COVARIANCE-AWARE FEATURE ALIGNMENT WITH PRE-COMPUTED SOURCE STATISTICS FOR TEST-TIME ADAPTATION TO MULTIPLE IMAGE CORRUPTIONS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Adachi, Kazuki Yamaguchi, Shin'ya Kumagai, Atsutoshi NTT Computer and Data Science Laboratories Japan Kyoto University Japan

Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and process images sent from various environments, such as cameras distributed in cities or cars. Such single models face images corrupted in heterogeneous ways in test time. Thus, they require to instantly adapt to the multiple corruptions during testing rather than being re-trained at a high cost. Test-time adaptation (TTA), which aims to adapt models without accessing the training dataset, is one of the settings that can address this problem. Existing TTA methods indeed work well on a single corruption. However, the adaptation ability is limited when multiple types of corruption occur, which is more realistic. We hypothesize this is because the distribution shift is more complicated, and the adaptation becomes more difficult in case of multiple corruptions. In fact, we experimentally found that a larger distribution gap remains after TTA. To address the distribution gap during testing, we propose a novel TTA method named Covariance-Aware Feature alignment (CAFe). We empirically show that CAFe outperforms prior TTA methods on image corruptions, including multiple types of corruptions. Copyright © 2022, The Authors. All rights reserved.

关键词： Crime

Circuit designs for practical-scale fault-tolerant quantum computing

学校读者我要写书评

暂无评论

Circuit designs for practical-scale fault-tolerant quantum c...

2023 IEEE Symposium on VLSI Technology and Circuits, VLSI Technology and Circuits 2023

作者： Suzuki, Yasunari Ueno, Yosuke Liao, Wang Tanaka, Masamitsu Tanimoto, Teruo Ntt Computer & Data Science Laboratories Tokyo Musashino Japan Jst Resto Kawaguchi Saitama Japan Keio University Kanagawa Yokohama Japan The University of Tokyo Bunkyo-ku Tokyo Japan Nagoya University Aichi Nagoya Japan Kyushu University Fukuoka Japan

ISBN: (纸本)9784863488069

To demonstrate reliable and scalable quantum computation, we need quantum error correction to reduce its error rates. One of the most challenging parts of implementing quantum error correction is to design error-decoding units, which estimate errors during computation. We estimate the required performances of error-decoding units to run practical-scale quantum algorithms and discuss the directions to satisfy them. © 2023 JSAP.

关键词： Quantum computers