Non-Asymptotic Performance of Social Machine Learning Under Limited Data

• URL: http://arxiv.org/abs/2306.09397v2
• Date: Tue, 9 Jul 2024 17:39:58 GMT
• Title: Non-Asymptotic Performance of Social Machine Learning Under Limited Data
• Authors: Ping Hu, Virginia Bordignon, Mert Kayaalp, Ali H. Sayed,
• Abstract summary: This paper studies the probability of error associated with the social machine learning framework. It addresses the problem of classifying a stream of unlabeled data in a distributed manner.
• Score: 45.48644055449902
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper studies the probability of error associated with the social machine learning framework, which involves an independent training phase followed by a cooperative decision-making phase over a graph. This framework addresses the problem of classifying a stream of unlabeled data in a distributed manner. In this work, we examine the classification task with limited observations during the decision-making phase, which requires a non-asymptotic performance analysis. We establish a condition for consistent training and derive an upper bound on the probability of error for classification. The results clarify the dependence on the statistical properties of the data and the combination policy used over the graph. They also establish the exponential decay of the probability of error with respect to the number of unlabeled samples.

Related papers

• Mind the Graph When Balancing Data for Fairness or Robustness [73.03155969727038]
  We define conditions on the training distribution for data balancing to lead to fair or robust models. Our results show that, in many cases, the balanced distribution does not correspond to selectively removing the undesired dependencies. Overall, our results highlight the importance of taking the causal graph into account before performing data balancing.
  arXiv  Detail & Related papers  (2024-06-25T10:16:19Z)
• Learning Latent Graph Structures and their Uncertainty [63.95971478893842]
  Graph Neural Networks (GNNs) use relational information as an inductive bias to enhance the model's accuracy. As task-relevant relations might be unknown, graph structure learning approaches have been proposed to learn them while solving the downstream prediction task.
  arXiv  Detail & Related papers  (2024-05-30T10:49:22Z)
• Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learning [1.6752182911522522]
  We show that uncertainty sampling is sufficient to achieve exploration versus exploitation in graph-based active learning. In particular, we use a recently developed algorithm, Poisson ReWeighted Laplace Learning (PWLL) for the classifier. We present experimental results on a number of graph-based image classification problems.
  arXiv  Detail & Related papers  (2022-10-27T22:07:53Z)
• Generalization bounds and algorithms for estimating conditional average treatment effect of dosage [13.867315751451494]
  We investigate the task of estimating the conditional average causal effect of treatment-dosage pairs from a combination of observational data and assumptions on the causal relationships in the underlying system. This has been a longstanding challenge for fields of study such as epidemiology or economics that require a treatment-dosage pair to make decisions. We show empirically new state-of-the-art performance results across several benchmark datasets for this problem.
  arXiv  Detail & Related papers  (2022-05-29T15:26:59Z)
• Fairness constraint in Structural Econometrics and Application to fair estimation using Instrumental Variables [3.265773263570237]
  A supervised machine learning algorithm determines a model from a learning sample that will be used to predict new observations. This information aggregation does not consider any potential selection on unobservables and any status-quo biases which may be contained in the training sample. The latter bias has raised concerns around the so-called textitfairness of machine learning algorithms, especially towards disadvantaged groups.
  arXiv  Detail & Related papers  (2022-02-16T15:34:07Z)
• Learning from Heterogeneous Data Based on Social Interactions over Graphs [58.34060409467834]
  This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions. We show that the. strategy enables the agents to learn consistently under this highly-heterogeneous setting. We show that the. strategy enables the agents to learn consistently under this highly-heterogeneous setting.
  arXiv  Detail & Related papers  (2021-12-17T12:47:18Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)
• Accounting for Unobserved Confounding in Domain Generalization [107.0464488046289]
  This paper investigates the problem of learning robust, generalizable prediction models from a combination of datasets. Part of the challenge of learning robust models lies in the influence of unobserved confounders. We demonstrate the empirical performance of our approach on healthcare data from different modalities.
  arXiv  Detail & Related papers  (2020-07-21T08:18:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.