Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing

• URL: http://arxiv.org/abs/2602.23565v1
• Date: Fri, 27 Feb 2026 00:21:36 GMT
• Title: Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing
• Authors: Adhyyan Narang, Sarah Dean, Lillian J Ratliff, Maryam Fazel,
• Abstract summary: We propose an algorithm that allows learners to "probe" the predictions of peer models, enabling them to learn about users who do not select them.<n>Our analysis characterizes when probing succeeds: this procedure converges almost surely to a stationary point with bounded full-population risk.<n>We verify our findings with semi-synthetic experiments on the MovieLens, Census, and Amazon Sentiment datasets.
• Score: 28.675614560503707
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In many economically relevant contexts where machine learning is deployed, multiple platforms obtain data from the same pool of users, each of whom selects the platform that best serves them. Prior work in this setting focuses exclusively on the "local" losses of learners on the distribution of data that they observe. We find that there exist instances where learners who use existing algorithms almost surely converge to models with arbitrarily poor global performance, even when models with low full-population loss exist. This happens through a feedback-induced mechanism, which we call the overspecialization trap: as learners optimize for users who already prefer them, they become less attractive to users outside this base, which further restricts the data they observe. Inspired by the recent use of knowledge distillation in modern ML, we propose an algorithm that allows learners to "probe" the predictions of peer models, enabling them to learn about users who do not select them. Our analysis characterizes when probing succeeds: this procedure converges almost surely to a stationary point with bounded full-population risk when probing sources are sufficiently informative, e.g., a known market leader or a majority of peers with good global performance. We verify our findings with semi-synthetic experiments on the MovieLens, Census, and Amazon Sentiment datasets.

Related papers

• Heterogeneity-Aware Client Selection Methodology For Efficient Federated Learning [2.154836869144035]
  Federated Learning (FL) enables a distributed client-server architecture where multiple clients collaboratively train a global Machine Learning (ML) model without sharing sensitive local data.<n>FL often results in lower accuracy than traditional ML algorithms due to statistical heterogeneity across clients.<n>We introduce Terraform, a novel client selection methodology that uses gradient updates and a deterministic selection algorithm to select heterogeneous clients for retraining.
  arXiv  Detail & Related papers  (2026-02-24T01:19:10Z)
• Boosting Federated Learning with FedEntOpt: Mitigating Label Skew by Entropy-Based Client Selection [13.851391819710367]
  Deep learning domains typically require an extensive amount of data for optimal performance.<n>FedEntOpt is designed to mitigate performance issues caused by label distribution skew.<n>It exhibits robust and superior performance in scenarios with low participation rates and client dropout.
  arXiv  Detail & Related papers  (2024-11-02T13:31:36Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Federated Skewed Label Learning with Logits Fusion [23.062650578266837]
  Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. We propose FedBalance, which corrects the optimization bias among local models by calibrating their logits. Our method can gain 13% higher average accuracy compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-11-14T14:37:33Z)
• Federated Learning on Non-iid Data via Local and Global Distillation [25.397058380098816]
  We propose FedND: federated learning with noise distillation. In the client, we propose a self-distillation method to train the local model. In the server, we generate noisy samples for each client and use them to distill other clients. Experimental results show that the algorithm achieves the best performance and is more communication-efficient than state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-06-26T06:14:01Z)
• ASPEST: Bridging the Gap Between Active Learning and Selective Prediction [56.001808843574395]
  Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples. In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
  arXiv  Detail & Related papers  (2023-04-07T23:51:07Z)
• Non-Invasive Fairness in Learning through the Lens of Data Drift [88.37640805363317]
  We show how to improve the fairness of Machine Learning models without altering the data or the learning algorithm. We use a simple but key insight: the divergence of trends between different populations, and, consecutively, between a learned model and minority populations, is analogous to data drift. We explore two strategies (model-splitting and reweighing) to resolve this drift, aiming to improve the overall conformance of models to the underlying data.
  arXiv  Detail & Related papers  (2023-03-30T17:30:42Z)
• DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics [60.60173139258481]
  Local training on non-iid distributed data results in deflected local optimum. A natural solution is to gather all client data onto the server, such that the server has a global view of the entire data distribution. In this paper, we put forth an idea to collect and leverage global knowledge on the server without hindering data privacy.
  arXiv  Detail & Related papers  (2022-11-20T06:13:06Z)
• Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning [92.89846887298852]
  Consider making a prediction over new test data without any opportunity to learn from a training set of labelled data. Give access to a set of expert models and their predictions alongside some limited information about the dataset used to train them.
  arXiv  Detail & Related papers  (2022-10-11T10:20:31Z)
• SCEI: A Smart-Contract Driven Edge Intelligence Framework for IoT Systems [15.796325306292134]
  Federated learning (FL) enables collaborative training of a shared model on edge devices while maintaining data privacy. Various personalized approaches have been proposed, but such approaches fail to handle underlying shifts in data distribution. This paper presents a dynamically optimized personal deep learning scheme based on blockchain and federated learning.
  arXiv  Detail & Related papers  (2021-03-12T02:57:05Z)
• Analysis and Optimal Edge Assignment For Hierarchical Federated Learning on Non-IID Data [43.32085029569374]
  Federated learning algorithms aim to leverage distributed and diverse data stored at users' devices to learn a global phenomena. In the cases where the participants' data are strongly skewed (i.e., non-IID), the local models can overfit local data, leading to low performing global model. We propose a hierarchical learning system that performs Federated Gradient Descent on the user-edge layer and Federated Averaging on the edge-cloud layer.
  arXiv  Detail & Related papers  (2020-12-10T12:18:13Z)
• Multi-Center Federated Learning [62.57229809407692]
  This paper proposes a novel multi-center aggregation mechanism for federated learning. It learns multiple global models from the non-IID user data and simultaneously derives the optimal matching between users and centers. Our experimental results on benchmark datasets show that our method outperforms several popular federated learning methods.
  arXiv  Detail & Related papers  (2020-05-03T09:14:31Z)

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.