检索结果-内蒙古大学图书馆

PDSL: Privacy-Preserved Decentralized Stochastic learning with Heterogeneous Data Distribution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Lina Yuan, Yunsheng Wang, Chunxiao Li, Feng School of Computer Science and Technology Shandong University Qingdao China Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

In the paradigm of decentralized learning, a group of agents collaborates to learn a global model using distributed datasets without a central server. However, due to the heterogeneity of the local data across the different agents, learning a robust global model is rather challenging. Moreover, the collaboration of the agents relies on their gradient information exchange, which poses a risk of privacy leakage. In this paper, to address these issues, we propose PDSL, a novel privacy-preserved decentralized stochastic learning algorithm with heterogeneous data distribution. On one hand, we innovate in utilizing the notion of Shapley values such that each agent can precisely measure the contributions of its heterogeneous neighbors to the global learning goal;on the other hand, we leverage the notion of differential privacy to prevent each agent from suffering privacy leakage when it contributes gradient information to its neighbors. We conduct both solid theoretical analysis and extensive experiments to demonstrate the efficacy of our PDSL algorithm in terms of privacy preservation and convergence. © 2025, CC BY-NC-ND.

关键词： learning algorithms

Ensemble of One Model: Creating Model Variations for Transformer with Layer Permutation

学校读者我要写书评

暂无评论

Ensemble of One Model: Creating Model Variations for Transfo...

2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021

作者： Liaw, Andrew Hsu, Jia-Hao Wu, Chung-Hsien National Cheng Kung University Department of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9789881476890

Ensemble involves combining the outputs of multiple models to increase performance. This technique has enjoyed great success across many fields in machine learning. This study focuses on a novel approach to increase performance of a model without any increase in number of parameters. The proposed approach involves training a model that can have different variations that perform well and different enough for ensemble. The variations are created by changing the order of the layers of a machine learning model. Moreover, this method can be combined with existing ensemble technique to further improve the performance. The task chosen for evaluating the performance is machine translation with Transformer, as Transformer is the current state-of-the-art model for this task as well as many natural language processing tasks. The IWSLT 2014 German to English and French to English datasets see an increase of at least 0.7 BLEU score over single model baseline with the same model size. When combined with multiple model ensemble, minimum increase of 0.3 BLEU is observed with no increase in parameters. © 2021 APSIPA.

关键词： learning algorithms

Constrained Machine learning Through Hyperspherical Representation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Signorelli, Gaetano Lombardi, Michele University of Bologna Italy

The problem of ensuring constraints satisfaction on the output of machine learning models is critical for many applications, especially in safety-critical domains. Modern approaches rely on penalty-based methods at training time, which do not guarantee to avoid constraints violations;or constraint-specific model architectures (e.g., for monotonocity);or on output projection, which requires to solve an optimization problem that might be computationally demanding. We present the Hypersherical Constrained Representation, a novel method to enforce constraints in the output space for convex and bounded feasibility regions (generalizable to star domains). Our method operates on a different representation system, where Euclidean coordinates are converted into hyperspherical coordinates relative to the constrained region, which can only inherently represent feasible points. Experiments on a synthetic and a real-world dataset show that our method has predictive performance comparable to the other approaches, can guarantee 100% constraint satisfaction, and has a minimal computational cost at inference time. Copyright © 2025, The Authors. All rights reserved.

关键词： learning algorithms

Gating is Weighting: Understanding Gated Linear Attention through In-context learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Yingcong Tarzanagh, Davoud Ataee Rawat, Ankit Singh Fazel, Maryam Oymak, Samet University of Michigan United States University of Pennsylvania United States Google Research NYC United States University of Washington United States

Linear attention methods offer a compelling alternative to softmax attention due to their efficiency in recurrent decoding. Recent research has focused on enhancing standard linear attention by incorporating gating while retaining its computational benefits. Such Gated Linear Attention (GLA) architectures include competitive models such as Mamba and RWKV. In this work, we investigate the in-context learning capabilities of the GLA model and make the following contributions. We show that a multilayer GLA can implement a general class of Weighted Preconditioned Gradient Descent (WPGD) algorithms with data-dependent weights. These weights are induced by the gating mechanism and the input, enabling the model to control the contribution of individual tokens to prediction. To further understand the mechanics of this weighting, we introduce a novel data model with multitask prompts and characterize the optimization landscape of learning a WPGD algorithm. Under mild conditions, we establish the existence and uniqueness (up to scaling) of a global minimum, corresponding to a unique WPGD solution. Finally, we translate these findings to explore the optimization landscape of GLA and shed light on how gating facilitates context-aware learning and when it is provably better than vanilla linear attention. © 2025, CC BY.

关键词： learning algorithms

A quantitative reward prediction error signal in the ventral pallidum

学校读者我要写书评

暂无评论

NATURE NEUROSCIENCE 2020年第10期23卷 1267-+页

作者： Ottenheimer, David J. Bari, Bilal A. Sutlief, Elissa Fraser, Kurt M. Kim, Tabitha H. Richard, Jocelyn M. Cohen, Jeremiah Y. Janak, Patricia H. Johns Hopkins Univ Solomon H Snyder Dept Neurosci Baltimore MD 21218 USA Johns Hopkins Univ Brain Sci Inst Baltimore MD USA Johns Hopkins Univ Dept Psychol & Brain Sci Baltimore MD 21218 USA Univ Minnesota Dept Neurosci Minneapolis MN USA Johns Hopkins Univ Kavli Neurosci Discovery Inst Baltimore MD 21218 USA

The nervous system is hypothesized to compute reward prediction errors (RPEs) to promote adaptive behavior. Correlates of RPEs have been observed in the midbrain dopamine system, but the extent to which RPE signals exist in other reward-processing regions is less well understood. In the present study, we quantified outcome history-based RPE signals in the ventral pallidum (VP), a basal ganglia region functionally linked to reward-seeking behavior. We trained rats to respond to reward-predicting cues, and we fit computational models to predict the firing rates of individual neurons at the time of reward delivery. We found that a subset of VP neurons encoded RPEs and did so more robustly than the nucleus accumbens, an input to the VP. VP RPEs predicted changes in task engagement, and optogenetic manipulation of the VP during reward delivery bidirectionally altered rats' subsequent reward-seeking behavior. Our data suggest a pivotal role for the VP in computing teaching signals that influence adaptive reward seeking. The nervous system is hypothesized to calculate reward prediction errors to estimate reward availability in the environment. The authors quantify a robust prediction error signal in the ventral pallidum derived from recently received rewarding outcomes.

关键词： learning algorithms Motivation Operant learning Reward

Design and implementation of fertilizer recommendation system for farmers

学校读者我要写书评

暂无评论

Test Engineering and Management 2020年 83卷 8840-8849页

作者： Usha Kiruthika, S. Kanaga Suba Raja, S. Ronak, S.R. Rengarajen, S. Ravindran, P. Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai India Easwari Engineering College Chennai India

India is an agrarian nation. But creating a profitable yield for the farmer in each crop cycle is becoming a major challenge on various factors. Picking the reasonable fertilizer for the land and yield is an important and basic part of agriculture. Deciding the supplement levels in soil utilizing lab hardware can be restrictively costly, particularly in developing nations. The current frameworks on deciding soil nutrient substance and proposal for fertilizer isn't sufficiently proficient efficient enough. This paper introduces a compelling technique for estimation of nutrient dimension in soil and suggestion for appropriate fertilizer. The proposed methodologies comprise of four stages: soil analysis, data pre-processing, data analysis and Recommendation. The soil sample is analyzed using an IoT based device utilizing NPK sensor with two electrodes are set to calculate collect the NPK ratio of the soil nutrient and for pre-processing, the data gathered from sensors are figured into correct dataset and machine learning algorithm is utilized to recognize the reasonable fertilizer. This venture is extremely valuable to farmer to pick the right fertilizer toward the start of product cycle and amplify the yield. © 2020 Mattingley Publishing. All rights reserved.

关键词： learning algorithms

An Effective Search Economics Based Feature Selection Algorithm for Passenger Flow Prediction

学校读者我要写书评

暂无评论

An Effective Search Economics Based Feature Selection Algori...

5th IEEE International Conference on Smart Internet of Things, SmartIoT 2021

作者： Chen, Jyun-Teng Tsai, Chun-Wei Chiang, Ming-Chao Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan

ISBN: (纸本)9781665445115

The amount of raw data for passenger flow is typically large, and different features of such data may have different impacts on the performance of a machine learning algorithm. As a consequence, an effective feature selection method is needed to select features that are important while at the same time filtering out features that are unimportant so as to both reduce the computation time and improve the accuracy of passenger flow prediction. Several previous results show that metaheuristic algorithms provide an effective way for feature selection compared to rule-based methods. In this study, an effective metaheuristic algorithm is presented for selecting valuable features out of a passenger flow dataset (from Taipei Rapid Transit Corporation) so as to improve the accuracy of a deep learning algorithm for predicting the number of passengers in the Taipei metro station. The proposed algorithm is based on a novel metaheuristic algorithm called search economics (SE) that divides the solution space into a set of regions and searches these regions based on the potential of each region to find a better solution. Simulation results show that feature selection based on SE can achieve the lowest prediction error compared with other state-of-the-art methods, such as grey wolf optimization, grasshopper optimization algorithm, and particle swarm optimization. © 2021 IEEE.

关键词： learning algorithms

Compositional federated learning: Applications in distributionally robust averaging and meta learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Feihu Li, Junyi College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Department of Electrical and Computer Engineering University of Pittsburgh United States

In the paper, we propose an effective and efficient Compositional Federated learning (ComFedL) algorithm for solving a new compositional Federated learning (FL) framework, which frequently appears in many data mining and machine learning problems with a hierarchical structure such as distributionally robust FL and model-agnostic meta learning (MAML). Moreover, we study the convergence analysis of our ComFedL algorithm under some mild conditions, and prove that it achieves a convergence rate of O(1/√T), where T denotes the number of iteration. To the best of our knowledge, our new Compositional FL framework is the first work to bridge federated learning with composition stochastic optimization. In particular, we first transform the distributionally robust FL (i.e., a minimax optimization problem) into a simple composition optimization problem by using KL divergence regularization. At the same time, we also first transform the distribution-agnostic MAML problem (i.e., a minimax optimization problem) into a simple yet effective composition optimization problem. Finally, we apply two popular machine learning tasks, i.e., distributionally robust FL and MAML to demonstrate the effectiveness of our algorithm. © 2021, CC BY-NC-ND.

关键词： learning algorithms

Causal representation learning in offline visual reinforcement learning

学校读者我要写书评

暂无评论

Knowledge-Based Systems 2025年 320卷

作者： Zhang, Yaru Chen, Kaizhou Liu, Yunlong Department of Automation Xiamen University Xiamen361005 China

Real-world reinforcement learning (RL) applications contend with high-dimensional visual observations contaminated by confounding factors, which induce spurious correlations and obscure decision-relevant information. Compounding this issue, the inability to interact online necessitates reliance on pre-collected datasets, thereby hampering a deeper understanding of complex environment structures. In this work, by focusing on the causal rather than spurious correlations in the input and explicitly distinguishing between task-related and task-irrelevant elements of the causal variables, we propose a mask-based algorithm for learning task-related minimal causal state representations, namely MMCS. Specifically, MMCS guides the decoupling of minimal causal variables through mask network partitioning and jointly enforcing conditional independence and causal sufficiency, thereby eliminating unnecessary dependencies between variables and uncovering causal dependency structures. More importantly, MMCS is decoupled from downstream policy learning, and can function as a plug-in method compatible with any offline reinforcement learning algorithm. Empirical results on the Visual-D4RL benchmark demonstrate that MMCS significantly improves performance and sample efficiency in downstream policy learning. In addition, its robust performance in various distraction environments highlights the potential of MMCS to improve the generalizability of offline RL, especially under conditions of limited data and visual distractions. Code is available at https://***/DMU-XMU/***. © 2025 Elsevier B.V.

关键词： learning algorithms