检索结果-内蒙古大学图书馆

Federated Learning and Differential Privacy: Software tools analysis, the *** FL framework and methodological guidelines for preserving data privacy

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rodríguez-Barroso, Nuria Stipcich, Goran Jiménez-López, Daniel Ruiz-Millán, José Antonio Martínez-Cámara, Eugenio González-Seco, Gerardo Luzón, M. Victoria Veganzones, Miguel Ángel Herrera, Francisco Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Spain Sherpa.ai Bilbao Spain

The high demand of artificial intelligence services at the edges that also preserve data privacy has pushed the research on novel machine learning paradigms that fit those requirements. Federated learning has the ambition to protect data privacy through distributed learning methods that keep the data in their data silos. Likewise, differential privacy attains to improve the protection of data privacy by measuring the privacy loss in the communication among the elements of federated learning. The prospective matching of federated learning and differential privacy to the challenges of data privacy protection has caused the release of several software tools that support their functionalities, but they lack of the needed unified vision for those techniques, and a methodological workflow that support their use. Hence, we present the *** Federated Learning framework that is built upon an holistic view of federated learning and differential privacy. It results from the study of how to adapt the machine learning paradigm to federated learning, and the definition of methodological guidelines for developing artificial intelligence services based on federated learning and differential privacy. We show how to follow the methodological guidelines with the *** Federated Learning framework by means of a classification and a regression use cases. Copyright © 2020, The Authors. All rights reserved.

关键词： Computer programming

Local-Global Methods for Generalised Solar Irradiance Forecasting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cargan, Timothy R. Landa-Silva, Dario Triguero, Isaac Lab School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom Department of Computer Science and Artificial Intelligence University of Granada Granada Spain DaSCI Andalusian Institute in Data Science and Computational Intelligence University of Granada Granada Spain

As the use of solar power increases, having accurate and timely forecasts will be essential for smooth grid operators. There are many proposed methods for forecasting solar irradiance / solar power production. However, many of these methods formulate the problem as a time-series, relying on near real-time access to observations at the location of interest to generate forecasts. This requires both access to a real-time stream of data and enough historical observations for these methods to be deployed. In this paper, we propose the use of Global methods to train our models in a generalised way, enabling them to generate forecasts for unseen locations. We apply this approach to both classical ML and state of the art methods. Using data from 20 locations distributed throughout the UK and widely available weather data, we show that it is possible to build systems that do not require access to this data. We utilise and compare both satellite and ground observations (e.g. temperature, pressure) of weather data. Leveraging weather observations and measurements from other locations we show it is possible to create models capable of accurately forecasting solar irradiance at new locations. This could facilitate use planning and optimisation for both newly deployed solar farms and domestic installations from the moment they come online. Additionally, we show that training a single global model for multiple locations can produce a more robust model with more consistent and accurate results across locations. © 2023, CC BY.

关键词： Location

A Group Decision-Making Approach Leveraging Preference Relations Derived from Large Language Model

学校读者我要写书评

暂无评论

Procedia Computer science 2024年 242卷 452-459页

作者： José Ramón Trillo María Ángeles Martínez Sławomir Zadrożny Janusz Kacprzyk Enrique Herrera-Viedma Francisco Javier Cabrerizo Department of Computer Science and Artificial Intelligence University of Granada Granada 18071 Spain Andalusian Research Institute of Data Science and Computational Intelligence DaSCI University of Granada Granada 18071 Spain Department of Social Work and Social Services University of Granada 18001 Granada Spain Systems Research Institute Polish Academy of Sciences Newelska 6 01-447 Warsaw Poland

Group decision-making involves selecting among limited options. Experts share their perspectives in a comparative debate but then evaluate alternatives using preference relations, which can result in inconsistencies between their expressions and assessments. To address this, a method is proposed that automates the generation of these relationships from the debate comments, classifying them into positive and negative using sentiment analysis, namely with the Large Language Model. A new operator is introduced that weights these comments to calculate preference relations. Furthermore, modification of the relationships is allowed if the experts so wish. Moreover, another operator is incorporated that adjusts the weight of each expert according to his or her active participation in the discussion, assigning more weight to those who contribute more comments. Finally, this innovative method promotes coherence and equal participation in group decision-making by employing an innovative sentiment analysis detection system.

关键词： Sentiment Analysis Large Language Model Group Decision-Making Detection System Consensus Method

Version Innovation Age and Age of Incorrect Version for Monitoring Markovian Sources

学校读者我要写书评

暂无评论

Version Innovation Age and Age of Incorrect Version for Moni...

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Mehrdad Salimnejad Marios Kountouris Anthony Ephremides Nikolaos Pappas Department of Computer and Information Science Linköping University Linköping Sweden Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Spain Electrical and Computer Engineering University of Maryland College Park MD USA

ISBN: (数字)9783903176652

ISBN: (纸本)9798331508722

In this paper, we study the problem of real-time remote tracking of a two-state Markov process. We introduce a modified randomized stationary sampling and transmission policy where the decision to perform sampling occurs probabilistically depending on the current state of the source and whether the system was in a sync state during the previous time slot or not. We then propose two new performance metrics, coined the Version Innovation Age (VIA) and the Age of Incorrect Version (AoIV), and analyze their performance under the modified randomized stationary and other state-of-the-art sampling and transmission policies. Specifically, we derive closed-form expressions for the distribution and the average of VIA and AoIV under these policies. Furthermore, we formulate and solve two constrained optimization problems. The first optimization problem aims to minimize the average VIA subject to constraints on the time-averaged sampling cost and time-averaged reconstruction error. In the second problem, the objective is to minimize the average AoIV while considering a constraint on the time-averaged sampling cost. Finally, we compare the performance of various sampling and transmission policies and identify the conditions under which each policy outperforms the others in optimizing the proposed metrics.

关键词： Measurement Technological innovation Costs Transmitters Wireless networks System performance Receivers Synchronization Optimization Monitoring

Looking Over the Research Literature on Software Engineering from 2016 to 2018

学校读者我要写书评

暂无评论

Procedia Computer science 2019年 162卷 712-719页

作者： Ruben Heradio David Fernandez-Amoros Daniel Galan Francisco Javier Cabrerizo Enrique Herrera-Viedma ETSI Informatica Universidad Nacional de Educacion a Distancia Madrid 28040 Spain Andalusian Research Institute in Data Science and Computational Intelligence University of Granada 18071 Granada Spain

This paper carries out a bibliometric analysis to detect (i) what is the most influential research on software engineering at the moment, (ii) where is being published that relevant research, (iii) what are the most commonly researched topics, (iv) and where is being undertaken that research (i.e., in which countries and institutions). For that, 6,365 software engineering articles, published from 2016 to 2018 on a variety of conferences and journals, are examined.

关键词： Bibliometric analysis Software engineering Scopus

Adaptive Payoff-driven Interaction in Networked Snowdrift Games

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiong, Xiaojin Yao, Yichao Feng, Minyu Chica, Manuel College of Artificial Intelligence Southwest University Chongqing400715 China Andalusian Research Institute DaSCI "Data Science and Computational Intelligence" University of Granada Granada18071 Spain School of Information and Physical Sciences The University of Newcastle CallaghanNSW2308 Australia

In social dilemmas, most interactions are transient and susceptible to restructuring, leading to continuous changes in social networks over time. Typically, agents assess the rewards of their current interactions and adjust their connections to optimize outcomes. In this paper, we introduce an adaptive network model in the snowdrift game to examine dynamic levels of cooperation and network topology, involving the potential for both the termination of existing connections and the establishment of new ones. In particular, we define the agent's asymmetric disassociation tendency toward their neighbors, which fundamentally determines the probability of edge dismantlement. The mechanism allows agents to selectively sever and rewire their connections to alternative individuals to refine partnerships. Our findings reveal that adaptive networks are particularly effective in promoting a robust evolution toward states of either pure cooperation or complete defection, especially under conditions of extreme cost-benefit ratios, as compared to static network models. Moreover, the dynamic restructuring of connections and the distribution of network degrees among agents are closely linked to the levels of cooperation in stationary states. Specifically, cooperators tend to seek broader neighborhoods when confronted with the invasion of multiple defectors. Copyright © 2024, The Authors. All rights reserved.

关键词： Defects

Balancing Performance, Efficiency and Robustness in Open-World Machine Learning via Evolutionary Multi-objective Model Compression

学校读者我要写书评

暂无评论

Balancing Performance, Efficiency and Robustness in Open-Wor...

International Joint Conference on Neural Networks (IJCNN)

作者： Javier Del Ser Aitor Martinez-Seras Miren Nekane Bilbao Jesus L. Lobo Ibai Laña Francisco Herrera TECNALIA Basque Research and Technology Alliance (BRTA) Derio Spain University of the Basque Country (UPV/EHU) Bilbao Spain Dept. of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

When deploying machine learning models on resource-constrained hardware, reducing the memory footprint required by the model without compromising its performance is critical. Moreover, in open-world scenarios models often operate in dynamic and unpredictable environments where the data distribution evolves over time. Robust models can generalize well to unforeseen circumstances, including out-of-distribution inputs that may not have been encountered during the training phase. This adaptability is essential to handle the inherent variability of real-world data. This work formulates a multi-objective optimization problem that aims at optimizing the quantization resolution of the parameters of an already trained machine learning model based on three conflicting goals: maximizing the performance of the model on its designated learning task, minimizing the memory footprint of the compressed model, and enhancing its robustness against out-of-distribution data. Given the complexity of the resulting combinatorial optimization problem, we employ multi-objective evolutionary algorithms to efficiently obtain an approximation of the Pareto front balancing among the aforementioned objectives. Experiments with a randomized neural network compressed under the proposed formulation are run over several benchmark classification datasets. Different multi-objective solvers are employed to compare their effectiveness in terms of the convergence and diversity of their produced Pareto estimations. Additionally, we assess the achieved equilibrium between the three objectives against a floating-point implementation of the same model. Our experiments reveal that both the computational resources and the robustness of the model can be optimized via evolutionary quantization without significantly sacrificing its performance for the task at hand.

关键词： Training Adaptation models Quantization (signal) computational modeling Neural networks Machine learning Evolutionary computation

An Initial Step Towards Stable Explanations for Multivariate Time Series Classifiers with LIME

学校读者我要写书评

暂无评论

An Initial Step Towards Stable Explanations for Multivariate...

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Han Meng Christian Wagner Isaac Triguero Computational Optimisation and Learning (COL) Lab School of Computer Science University of Nottingham Nottingham United Kingdom Lab for Uncertainty in Data and Decision Making (LUCID) School of Computer Science University of Nottingham Nottingham United Kingdom DaSCI Andalusian Institute in Data Science and Computational Intelligence University of Granada Granada Spain Department of Computer Science and Artificial Intelligence University of Granada Granada Spain

LIME, or ‘Local Interpretability Model-agnostic Explanations’ is a well-known post-hoc explanation technique for the interpretation of black-box models. While very useful, recent studies show that LIME suffers from stability problems: explanations provided for the same process can be different, making it difficult to trust their reliability. This paper investigates the stability of LIME when explaining multivariate time series classification problems. We demonstrate that due to the temporal dependency in time series data, the traditional artificial neighbour generation methods used in LIME have a higher risk of creating out-of-distribution inputs. We disucss how this behavior is one of the reasons resulting in unstable explanations. In addition, LIME weights neighbours based on user-defined hyperparameters which are problem-dependent and hard to tune, and we show how unsuitable hyperparameters can contribute to the generation of unstable explanations. As a preliminary step towards addressing these issues, we propose to employ a generative approach with an adaptive weighting method in the LIME framework. Specifically, we adopt a generative model based on variational autoencoder to create within-distribution neighbours, reducing the out-of-distribution problem, while the adaptive weight method eliminates the need for user-defined hyperparameters. Experiments on real-world datasets demonstrate the effectiveness of the proposed method in providing more stable explanations using the LIME framework.

关键词：

Lights and shadows in evolutionary deep learning: Taxonomy, critical methodological analysis, cases of study, learned lessons, recommendations and challenges

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Martinez, Aritz D. Del Ser, Javier Villar-Rodriguez, Esther Osaba, Eneko Poyatos, Javier Tabik, Siham Molina, Daniel Herrera, Francisco Derio48160 Spain Bilbao48013 Spain DaSCI Andalusian Institute of Data Science and Computational Intelligence University of Granada Granada18071 Spain P. Tecnologico Ed. 700. DerioBizkaia48170 Spain

Much has been said about the fusion of bio-inspired optimization algorithms and Deep Learning models for several purposes: from the discovery of network topologies and hyperparametric configurations with improved performance for a given task, to the optimization of the models parameters as a replacement for gradient-based solvers. Indeed, the literature is rich in proposals showcasing the application of assorted nature-inspired approaches for these tasks. In this work we comprehensively review and critically examine contributions made so far based on three axes, each addressing a fundamental question in this research avenue: a) optimization and taxonomy (Why?), including a historical perspective, definitions of optimization problems in Deep Learning, and a taxonomy associated with an in-depth analysis of the literature, b) critical methodological analysis (How?), which together with two case studies, allows us to address learned lessons and recommendations for good practices following the analysis of the literature, and c) challenges and new directions of research (What can be done, and what for?). In summary, three axes – optimization and taxonomy, critical analysis, and challenges – which outline a complete vision of a merger of two technologies drawing up an exciting future for this area of fusion research. Copyright © 2020, The Authors. All rights reserved.

关键词： Taxonomies