检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Hongkang Li Meng Wang Tengfei Ma Sijia Liu Zaixi Zhang Pin-Yu Chen Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute Troy NY Department of Biomedical Informatics Stony Brook University Stony Brook NY Department of Computer Science and Engineering Michigan State University East Lansing MI and MIT-IBM Watson AI Lab IBM Research MA Department of Computer Science and Engineering University of Science and Technology of China Hefei Anhui China IBM Thomas J. Watson Research Center Yorktown Heights NY

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trade-off between payoff and model rewards in shapley-fair collaborative machine learning 22

Trade-off between payoff and model rewards in shapley-fair c...

引用

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

作者： Quoc Phong Nguyen Bryan Kian Hsiang Low Patrick Jaillet Institute of Data Science National University of Singapore Republic of Singapore Dept. of Electrical Engineering and Computer Science MIT Dept. of Computer Science National University of Singapore Republic of Singapore

ISBN: (纸本)9781713871088

This paper investigates the problem of fairly trading off between payoff and model rewards in collaborative machine learning (ML) where parties aggregate their datasets together to obtain improved ML models over that of each party. Supposing parties can afford the optimal model trained on the aggregated dataset, we propose an allocation scheme that distributes the payoff fairly. Notably, the same scheme can be derived from two different approaches based on (a) desirable properties of the parties' payoffs or (b) that of the underlying payoff flows from one party to another. While the former is conceptually simpler, the latter can be used to handle the practical constraint on the budgets of parties. In particular, we propose desirable properties for achieving a fair adjustment of the payoff flows that can trade off between the model reward's performance and the payoff reward. We empirically demonstrate that our proposed scheme is a sensible solution in several scenarios of collaborative ML with different budget constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimode amplitude squeezing through cascaded nonlinear optical processes

arXiv

引用

arXiv 2024年

作者： Pontula, Sahil Salamin, Yannick Roques-Carmes, Charles Soljačić, Marin Department of Physics MIT CambridgeMA02139 United States Department of Electrical Engineering and Computer Science MIT CambridgeMA02139 United States Research Laboratory of Electronics MIT CambridgeMA02139 United States E. L. Ginzton Laboratories Stanford University 348 Via Pueblo StanfordCA United States

Multimode squeezed light is enticing for several applications, from squeezed frequency combs for spectroscopy to signal multiplexing in optical computing. To generate squeezing in multiple frequency modes, optical parametric oscillators have been vital in realizing multimode squeezed vacuum states through second-order nonlinear processes. However, most work has focused on generating multimode squeezed vacua and squeezing in mode superpositions (supermodes). Bright squeezing in multiple discrete frequency modes, if realized, could unlock novel applications in quantum-enhanced spectroscopy and optical quantum computing. Here, we show how Q factor engineering of a multimode nonlinear cavity with cascaded three wave mixing processes creates strong, spectrally tunable single mode output amplitude noise squeezing over 10 dB below the shot noise limit. In addition, we demonstrate squeezing for multiple discrete frequency modes above threshold. This bright squeezing arises from enhancement of the (noiseless) nonlinear rate relative to decay rates in the system due to the cascaded generation of photons in a single idler "bath" mode. A natural consequence of the strong nonlinear coupling in our system is the creation of an effective cavity in the synthetic frequency dimension that sustains Bloch oscillations in the modal energy distribution. Bloch mode engineering could provide an opportunity to better control nonlinear energy flow in the synthetic frequency dimension, with exciting applications in quantum random walks and topological photonics. Lastly, we show evidence of long-range correlations in amplitude noise between discrete frequency modes, pointing towards the potential of long-range entanglement in a synthetic frequency dimension. © 2024, CC BY.

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

Enhanced Prediction of Fuel Consumption and Carbon Emissions in Light-Duty Vehicles using Convolutional Recurrent Imputation Network

Enhanced Prediction of Fuel Consumption and Carbon Emissions...

引用

International Conference on computer, electrical & Communication engineering (ICCECE)

作者： T. Lalitha Jerzy Ryszard Szymański Marta Żurek-Mortka mithileysh Sathiyanarayanan K. R. Srilekha Computer Science School of Information Science Presidency University Bengaluru Karnataka India Department of Electrical Drives and Industrial Electronics Faculty of Transport Electrical Engineering and Computer Sciences Casimir Pulaski University of Radom Poland Europe Lukasiewicz Research Network Institute for Sustainable Technologies Kazimierza Pułaskiego Radom Poland Europe MIT Square London I M.Tech Integrated(Software Engineering) VIT University Vellore Tamilnadu India

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

Fuel utilization and emission estimation are essential for assessing the consequence of materials and strict emission control measures due to the startling rate of weather changes. The world's socioeconomic issues are significantly impacted by the growing worldwide average temperature and its effects on climate change. The melting of the polar ice caps, that is a direct result of this rise, leads to a number of other problems, such as the polar animal’s death, coastal flooding, and exposure to bacteria and earliest microorganisms that are frozen in the snow and could cause many more global pandemics and invisible illnesses. In this paper, Enhanced Prediction of Fuel Consumption and Carbon Emissions in Light-Duty Vehicles using Dynamic Graph Convolutional Recurrent Imputation Network (EP-FCCE-DGCRIN) are proposed.. The effectiveness of the EP-FCCE-DGCRIN technique is compared to other existing methods. This research offers evidence-based suggestions to lessen the environmental effects of vehicles for both manufacturers and consumers depending upon the outcomes of the Descriptive Statistics analysis.

关键词： Temperature measurement Pandemics Snow Sea measurements Carbon dioxide Imputation Fuels Vehicle dynamics Socioeconomics Meteorology

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation and Energy Efficient Dynamic Particle Swarm Optimisation in Heterogeneous Wireless Communication Networks

Resource Allocation and Energy Efficient Dynamic Particle Sw...

引用

Innovation in Technology (ASIANCON), Asian Conference on

作者： Anuradha Bhalerao Pawar G. Kannan T. Anuradha Vignesh V R. Kesavan Jose Anand A Department of Electronics Engineering MIT Academy of Engineering Alandi Pune Maharastra Department of Electronics and Communication Engineering Amrita College of Engineering and Technology Tamil Nadu Department of Electrical and Electronics Engineering KCG College of Technology Tamil Nadu India Department of Computer Science and Engineering Karpagam College of Engineering Tamil Nadu India Institute of Computer Science and Engineering Saveetha School of Engineering SIMTS Tamil Nadu India Department of Electronics and Communication Engineering KCG College of Technology Tamil Nadu India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

This paper investigates the difficult of beam policy in a multi-user peer-to-peer web linkage setting as part of our research. Using a network simulator, the dynamic particle swarm optimization is suggested for this. The challenge is to limit the maximum power consumption per relay, according to minimal Signal to Noise Ratio (SNR) guarantees, after a complete Channel State Information (CSI) is established. It has been established that the non-convex problem satisfies a potent duality. The twofold problem with the highest polynomial complexity was given as Semi Definite Programming (SDP). On the basis of the standards of the optimal dual variables, we looked at the best beam forming vectors for the initial problems in 3 different scenarios. This demonstrated whether the minimum Signal-to-Noise Ratio (SNR) prerequisite for each S-D pair has been met as well as whether a relay's electricity consumption varies among relays.

关键词： Technological innovation Quality of service Throughput Energy efficiency Vectors Peer-to-peer computing Particle swarm optimization Optimization Signal to noise ratio Testing

来源：评论

学校读者我要写书评

暂无评论

Effective dimension in bandit problems under censorship 22

Effective dimension in bandit problems under censorship

引用

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

作者： Gauthier Guinet Saurabh Amin Patrick Jaillet AWS AI Labs MIT and Dept. of Civil and Environmental Engineering & Laboratory for Information and Decision Systems MIT and Dept. of Electrical Engineering and Computer Science & Laboratory for Information and Decision Systems

ISBN: (纸本)9781713871088

In this paper, we study both multi-armed and contextual bandit problems in censored environments. Our goal is to estimate the performance loss due to censorship in the context of classical algorithms designed for uncensored environments. Our main contributions include the introduction of a broad class of censorship models and their analysis in terms of the effective dimension of the problem - a natural measure of its underlying statistical complexity and main driver of the regret bound. In particular, the effective dimension allows us to maintain the structure of the original problem at first order, while embedding it in a bigger space, and thus naturally leads to results analogous to uncensored settings. Our analysis involves a continuous generalization of the Elliptical Potential Inequality, which we believe is of independent interest. We also discover an interesting property of decision- making under censorship: a transient phase during which initial misspecification of censorship is self-corrected at an extra cost; followed by a stationary phase that reflects the inherent slowdown of learning governed by the effective dimension. Our results are useful for applications of sequential decision-making models where the feedback received depends on strategic uncertainty (e.g., agents' willingness to follow a recommendation) and/or random uncertainty (e.g., loss or delay in arrival of information).

关键词：

来源：评论

学校读者我要写书评

暂无评论

What did I sign? A study of the impenetrability of legalese in contracts 43

What did I sign? A study of the impenetrability of legalese ...

引用

43rd Annual Meeting of the Cognitive science Society: Comparative Cognition: Animal Minds, CogSci 2021

作者： Martínez, Eric Mollica, Francis Liu, Yufei Podrug, Anita Gibson, Edward Brain and Cognitive Sciences MIT Cambridge United States School of Informatics University of Edinburgh Edinburgh United Kingdom Psychology Wellesley College Wellesley United States Electrical Engineering and Computer Science MIT Cambridge United States

Legal documents, in the form of terms of service agreements and other private contracts, are now an increasingly prevalent part of everyday life. While legal documents have long been acknowledged to be difficult to understand without training, it remains an open question whether the ever-increasing exposure to contracts might have mitigated this difficulty. Moreover, insofar as this difficulty has persisted, there remains no systematic analysis of which linguistic structures contribute most heavily to the processing difficulty of legal texts, nor whether this difficulty is heightened for those with less language experience. Here, we investigate these issues, and in a well-powered experiment find evidence that (a) both recall and comprehension of legal propositions in a contract are hindered by use of a legal register relative to plain-English translations;(b) certain linguistic structures, such as center-embedding, hinder recall to a greater degree than others, such as passive voice;and (c) language experience influences comprehension of legal propositions. Surprisingly, language experience did not influence recall, nor was there an interaction between legal register and language experience on recall or comprehension. These findings suggest that legal language poses heightened difficulties for those with less language experience–who tend to be of lower socioeconomic status and with diminished access to the justice system–and that eliminating complex features of legalese would benefit those of all reading levels. © Cognitive science Society: Comparative Cognition: Animal Minds, CogSci *** rights reserved.

关键词： Contracts

来源：评论

学校读者我要写书评

暂无评论

Towards a Rigorous Evaluation of Explainability for Multivariate Time Series

SSRN

引用

SSRN 2023年

作者： Saluja, Rohit Malhi, Avleen Knapič, Samanta Främling, Kary Cavdar, Cicek Department of Computer Science Aalto University Konemiehentie 2 Espoo02150 Finland Department of Computing Science Umeå University Mit-huset Umeå90187 Sweden University of Warwick United Kingdom Department of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

Machine learning-based systems are rapidly gaining popularity and in-line with that, there has been a huge research surge in the field of explainability to ensure that machine learning models are reliable, fair, and can be held liable for the decision-making process. Explainable Artificial Intelligence (XAI) methods are typically deployed to debug black-box machine learning models but in comparison to tabular, text, and image data, explainability in time series is still relatively unexplored. The aim of this study was to achieve and evaluate model agnostic explainability in a time series forecasting problem. This work focused on proving a solution for a digital consultancy company aiming to find a data-driven approach in order to understand the effect of their sales related activities on the sales deals closed. The solution involved framing the problem as a time series forecasting problem to predict the sales deals and the explainability was achieved using two novel model agnostic explainability techniques, Local explainable model- agnostic explanations (LIME) and Shapley additive explanations (SHAP) which were evaluated using human evaluations. The results clearly indicate that the explanations produced by LIME and SHAP greatly helped lay humans in understanding the predictions made by the machine learning model. The presented work can easily be extended to any time series forecasting or classification scenario for achieving explainability and evaluating the produced explanations. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Paper Quality Assessment based on Individual Wisdom Metrics from Open Peer Review

arXiv

引用

arXiv 2025年

作者： Zahorodnii, Andrii van den Bosch, Jasper J.F. Charest, Ian Summerfield, Christopher Fiete, Ila R. Department of Electrical Engineering and Computer Science MIT United States Department of Brain and Cognitive Sciences McGovern Institute MIT United States School of Psychology University of Leeds United Kingdom Département de Psychologie Universit é de Montréal Canada Department of Experimental Psychology University of Oxford United Kingdom

This study proposes a data-driven framework for enhancing the accuracy and efficiency of scientific peer review through an open, bottom-up process that estimates reviewer quality. Traditional closed peer review systems, while essential for quality control, are often slow, costly, and subject to biases that can impede scientific progress. Here, we introduce a method that evaluates individual reviewer reliability by quantifying agreement with community consensus scores and applying Bayesian weighting to refine paper quality assessments. We analyze open peer review data from two major scientific conferences, and demonstrate that reviewer-specific quality scores significantly improve the reliability of paper quality estimation. Perhaps surprisingly, we find that reviewer quality scores are unrelated to authorship quality. Our model incorporates incentive structures to recognize high-quality reviewers and encourage broader coverage of submitted papers, thereby mitigating the common "rich-get-richer" pitfall of social media. These findings suggest that open peer review, with mechanisms for estimating and incentivizing reviewer quality, offers a scalable and equitable alternative for scientific publishing, with potential to enhance the speed, fairness, and transparency of the peer review process. Copyright © 2025, The Authors. All rights reserved.

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

Flexible context-driven sensory processing in dynamical vision models 24

Flexible context-driven sensory processing in dynamical visi...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Lakshmi Narasimhan Govindarajan Abhiram Iyer Valmiki Kothare Ila Fiete Department of Brain and Cognitive Sciences and McGovern Institute for Brain Research and K. Lisa Yang Integrative Computational Neuroscience (ICoN) MIT Cambridge MA Department of Electrical Engineering and Computer Science and McGovern Institute for Brain Research and K. Lisa Yang Integrative Computational Neuroscience (ICoN) MIT Cambridge MA Department of Brain and Cognitive Sciences MIT Cambridge MA

ISBN: (纸本)9798331314385

Visual representations become progressively more abstract along the cortical hierarchy. These abstract representations define notions like objects and shapes, but at the cost of spatial specificity. By contrast, low-level regions represent spatially local but simple input features. How do spatially non-specific representations of abstract concepts in high-level areas flexibly modulate the low-level sensory representations in appropriate ways to guide context-driven and goal-directed behaviors across a range of tasks? We build a biologically motivated and trainable neural network model of dynamics in the visual pathway, incorporating local, lateral, and feedforward synaptic connections, excitatory and inhibitory neurons, and longrange top-down inputs conceptualized as low-rank modulations of the input-driven sensory responses by high-level areas. We study this Dynamical Cortical network (DCnet) in a visual cue-delay-search task and show that the model uses its own cue representations to adaptively modulate its perceptual responses to solve the task, outperforming state-of-the-art DNN vision and LLM models. The model's population states over time shed light on the nature of contextual modulatory dynamics, generating predictions for experiments. We fine-tune the same model on classic psychophysics attention tasks, and find that the model closely replicates known reaction time results. This work represents a promising new foundation for understanding and making predictions about perturbations to visual processing in the brain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：