Collaborative Learning via Prediction Consensus

• URL: http://arxiv.org/abs/2305.18497v3
• Date: Tue, 14 Nov 2023 20:10:57 GMT
• Title: Collaborative Learning via Prediction Consensus
• Authors: Dongyang Fan, Celestine Mendler-D\"unner, Martin Jaggi
• Abstract summary: We consider a collaborative learning setting where the goal of each agent is to improve their own model by leveraging the expertise of collaborators. We propose a distillation-based method leveraging shared unlabeled auxiliary data, which is pseudo-labeled by the collective. We demonstrate empirically that our collaboration scheme is able to significantly boost the performance of individual models.
• Score: 38.89001892487472
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider a collaborative learning setting where the goal of each agent is to improve their own model by leveraging the expertise of collaborators, in addition to their own training data. To facilitate the exchange of expertise among agents, we propose a distillation-based method leveraging shared unlabeled auxiliary data, which is pseudo-labeled by the collective. Central to our method is a trust weighting scheme that serves to adaptively weigh the influence of each collaborator on the pseudo-labels until a consensus on how to label the auxiliary data is reached. We demonstrate empirically that our collaboration scheme is able to significantly boost the performance of individual models in the target domain from which the auxiliary data is sampled. By design, our method adeptly accommodates heterogeneity in model architectures and substantially reduces communication overhead compared to typical collaborative learning methods. At the same time, it can provably mitigate the negative impact of bad models on the collective.

Related papers

• On the effects of similarity metrics in decentralized deep learning under distributional shift [2.6763602268733626]
  Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging.
  arXiv  Detail & Related papers  (2024-09-16T20:48:16Z)
• Decentralized Personalized Federated Learning [4.5836393132815045]
  We focus on creating a collaboration graph that guides each client in selecting suitable collaborators for training personalized models. Unlike traditional methods, our formulation identifies collaborators at a granular level by considering greedy relations of clients. We achieve this through a bi-level optimization framework that employs a constrained algorithm.
  arXiv  Detail & Related papers  (2024-06-10T17:58:48Z)
• Federated Learning Can Find Friends That Are Advantageous [14.993730469216546]
  In Federated Learning (FL), the distributed nature and heterogeneity of client data present both opportunities and challenges. We introduce a novel algorithm that assigns adaptive aggregation weights to clients participating in FL training, identifying those with data distributions most conducive to a specific learning objective.
  arXiv  Detail & Related papers  (2024-02-07T17:46:37Z)
• Personalizing Federated Learning with Over-the-Air Computations [84.8089761800994]
  Federated edge learning is a promising technology to deploy intelligence at the edge of wireless networks in a privacy-preserving manner. Under such a setting, multiple clients collaboratively train a global generic model under the coordination of an edge server. This paper presents a distributed training paradigm that employs analog over-the-air computation to address the communication bottleneck.
  arXiv  Detail & Related papers  (2023-02-24T08:41:19Z)
• Decentralized Learning with Multi-Headed Distillation [12.90857834791378]
  Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other.
  arXiv  Detail & Related papers  (2022-11-28T21:01:43Z)
• Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization [77.8735802150511]
  We propose a cross-sample adversarial debiasing (CSAD) method to remove the bias information misused by the target task. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-08-11T21:17:02Z)
• Toward Understanding the Influence of Individual Clients in Federated Learning [52.07734799278535]
  Federated learning allows clients to jointly train a global model without sending their private data to a central server. We defined a new notion called em-Influence, quantify this influence over parameters, and proposed an effective efficient model to estimate this metric.
  arXiv  Detail & Related papers  (2020-12-20T14:34:36Z)
• Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
  We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
  arXiv  Detail & Related papers  (2020-06-12T12:23:50Z)
• Self-Supervised Relational Reasoning for Representation Learning [5.076419064097733]
  In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on unlabeled data. We propose a novel self-supervised formulation of relational reasoning that allows a learner to bootstrap a signal from information implicit in unlabeled data. We evaluate the proposed method following a rigorous experimental procedure, using standard datasets, protocols, and backbones.
  arXiv  Detail & Related papers  (2020-06-10T14:24:25Z)
• Federated Residual Learning [53.77128418049985]
  We study a new form of federated learning where the clients train personalized local models and make predictions jointly with the server-side shared model. Using this new federated learning framework, the complexity of the central shared model can be minimized while still gaining all the performance benefits that joint training provides.
  arXiv  Detail & Related papers  (2020-03-28T19:55:24Z)

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.