Algorithmic Collective Action in Machine Learning

• URL: http://arxiv.org/abs/2302.04262v2
• Date: Wed, 21 Jun 2023 05:54:37 GMT
• Title: Algorithmic Collective Action in Machine Learning
• Authors: Moritz Hardt, Eric Mazumdar, Celestine Mendler-D\"unner, Tijana Zrnic
• Abstract summary: We study algorithmic collective action on digital platforms that deploy machine learning algorithms. We propose a simple theoretical model of a collective interacting with a firm's learning algorithm. We conduct systematic experiments on a skill classification task involving tens of thousands of resumes from a gig platform for freelancers.
• Score: 28.748367295360115
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We initiate a principled study of algorithmic collective action on digital platforms that deploy machine learning algorithms. We propose a simple theoretical model of a collective interacting with a firm's learning algorithm. The collective pools the data of participating individuals and executes an algorithmic strategy by instructing participants how to modify their own data to achieve a collective goal. We investigate the consequences of this model in three fundamental learning-theoretic settings: the case of a nonparametric optimal learning algorithm, a parametric risk minimizer, and gradient-based optimization. In each setting, we come up with coordinated algorithmic strategies and characterize natural success criteria as a function of the collective's size. Complementing our theory, we conduct systematic experiments on a skill classification task involving tens of thousands of resumes from a gig platform for freelancers. Through more than two thousand model training runs of a BERT-like language model, we see a striking correspondence emerge between our empirical observations and the predictions made by our theory. Taken together, our theory and experiments broadly support the conclusion that algorithmic collectives of exceedingly small fractional size can exert significant control over a platform's learning algorithm.

Related papers

• A Kernel Perspective on Distillation-based Collaborative Learning [8.971234046933349]
  We propose a nonparametric collaborative learning algorithm that does not directly share local data or models in statistically heterogeneous environments. Inspired by our theoretical results, we also propose a practical distillation-based collaborative learning algorithm based on neural network architecture.
  arXiv  Detail & Related papers  (2024-10-23T06:40:13Z)
• The Role of Learning Algorithms in Collective Action [8.955918346078935]
  We show that the effective size and success of a collective are highly dependent on the properties of the learning algorithm. This highlights the necessity of taking the learning algorithm into account when studying the impact of collective action in machine learning.
  arXiv  Detail & Related papers  (2024-05-10T16:36:59Z)
• Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning [7.8583640700306585]
  We develop algorithms based on optimization criteria inspired by a hierarchical Bayesian statistical framework. We develop adaptive algorithms that discover the balance between using limited local data and collaborative information. We evaluate our proposed algorithms using synthetic and real data, demonstrating the effective sample amplification for personalized tasks.
  arXiv  Detail & Related papers  (2024-02-19T20:53:27Z)
• A Reinforcement Learning-assisted Genetic Programming Algorithm for Team Formation Problem Considering Person-Job Matching [70.28786574064694]
  A reinforcement learning-assisted genetic programming algorithm (RL-GP) is proposed to enhance the quality of solutions. The hyper-heuristic rules obtained through efficient learning can be utilized as decision-making aids when forming project teams.
  arXiv  Detail & Related papers  (2023-04-08T14:32:12Z)
• CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning [50.90384817689249]
  CoopInit is a cooperative learning-based strategy that can quickly learn a good starting point for GANs. We demonstrate the effectiveness of the proposed approach on image generation and one-sided unpaired image-to-image translation tasks.
  arXiv  Detail & Related papers  (2023-03-21T07:49:32Z)
• Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness [92.26039686430204]
  We show that even in carefully-designed systems, complementary performance can be elusive. First, we provide a theoretical framework for modeling simple human-algorithm systems. Next, we use this model to prove conditions where complementarity is impossible.
  arXiv  Detail & Related papers  (2022-02-17T18:44:41Z)
• Towards Model Agnostic Federated Learning Using Knowledge Distillation [9.947968358822951]
  In this work, we initiate a theoretical study of model agnostic communication protocols. We focus on the setting where the two agents are attempting to perform kernel regression using different kernels. Our study yields a surprising result -- the most natural algorithm of using alternating knowledge distillation (AKD) imposes overly strong regularization.
  arXiv  Detail & Related papers  (2021-10-28T15:27:51Z)
• A black-box adversarial attack for poisoning clustering [78.19784577498031]
  We propose a black-box adversarial attack for crafting adversarial samples to test the robustness of clustering algorithms. We show that our attacks are transferable even against supervised algorithms such as SVMs, random forests, and neural networks.
  arXiv  Detail & Related papers  (2020-09-09T18:19:31Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• Three Approaches for Personalization with Applications to Federated Learning [68.19709953755238]
  We present a systematic learning-theoretic study of personalization. We provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance. All of our algorithms are model-agnostic and work for any hypothesis class.
  arXiv  Detail & Related papers  (2020-02-25T01:36:43Z)

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.