On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists

• URL: http://arxiv.org/abs/2409.13931v2
• Date: Tue, 1 Oct 2024 21:18:07 GMT
• Title: On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
• Authors: Dongyang Fan, Bettina Messmer, Martin Jaggi,
• Abstract summary: We propose a novel $textbfCo$llaborative learning approach with a $textbfMi$xture of $textbfG$eneralists and $textbfS$pecialists (CoMiGS) Our approach distinguishes generalists and specialists by aggregating certain experts across end users while keeping others localized to specialize in user-specific datasets.
• Score: 33.68104398807581
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-device LLMs have gained increasing attention for their ability to enhance privacy and provide a personalized user experience. To facilitate learning with private and scarce local data, federated learning has become a standard approach, though it introduces challenges related to system and data heterogeneity among end users. As a solution, we propose a novel $\textbf{Co}$llaborative learning approach with a $\textbf{Mi}$xture of $\textbf{G}$eneralists and $\textbf{S}$pecialists (CoMiGS), being the first to effectively address both. Our approach distinguishes generalists and specialists by aggregating certain experts across end users while keeping others localized to specialize in user-specific datasets. A key innovation of our method is the bi-level optimization formulation of the Mixture-of-Experts learning objective, where the router is updated using a separate validation set that represents the target distribution. CoMiGS effectively balances collaboration and personalization, as demonstrated by its superior performance in scenarios with high data heterogeneity across multiple datasets. By design, our approach accommodates users' varying computational resources through different numbers of specialists. By decoupling resource abundance from data quantity, CoMiGS remains robust against overfitting-due to the generalists' regularizing effect-while adapting to local data through specialist expertise.

Related papers

• Personalized Federated Learning for Cross-view Geo-localization [49.40531019551957]
  We propose a methodology combining Federated Learning (FL) with Cross-view Image Geo-localization (CVGL) techniques. Our method implements a coarse-to-fine approach, where clients share only the coarse feature extractors while keeping fine-grained features specific to local environments. Results demonstrate that our federated CVGL method achieves performance close to centralized training while maintaining data privacy.
  arXiv  Detail & Related papers  (2024-11-07T13:25:52Z)
• Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach [49.63614966954833]
  Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. To effectively train the proposed framework, we model the problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction.
  arXiv  Detail & Related papers  (2024-08-16T05:49:14Z)
• Personalized Federated Learning via Amortized Bayesian Meta-Learning [21.126405589760367]
  We introduce a new perspective on personalized federated learning through Amortized Bayesian Meta-Learning. Specifically, we propose a novel algorithm called emphFedABML, which employs hierarchical variational inference across clients. Our theoretical analysis provides an upper bound on the average generalization error and guarantees the generalization performance on unseen data.
  arXiv  Detail & Related papers  (2023-07-05T11:58:58Z)
• Personalized Federated Learning with Feature Alignment and Classifier Collaboration [13.320381377599245]
  Data heterogeneity is one of the most challenging issues in federated learning. One such approach in deep neural networks based tasks is employing a shared feature representation and learning a customized classifier head for each client. In this work, we conduct explicit local-global feature alignment by leveraging global semantic knowledge for learning a better representation.
  arXiv  Detail & Related papers  (2023-06-20T19:58:58Z)
• FedJETs: Efficient Just-In-Time Personalization with Federated Mixture of Experts [48.78037006856208]
  FedJETs is a novel solution by using a Mixture-of-Experts (MoE) framework within a Federated Learning (FL) setup. Our method leverages the diversity of the clients to train specialized experts on different subsets of classes, and a gating function to route the input to the most relevant expert(s) Our approach can improve accuracy up to 18% in state of the art FL settings, while maintaining competitive zero-shot performance.
  arXiv  Detail & Related papers  (2023-06-14T15:47:52Z)
• Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization [57.98426940386627]
  We show that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-02-10T20:44:44Z)
• Federated Mixture of Experts [94.25278695272874]
  FedMix is a framework that allows us to train an ensemble of specialized models. We show that users with similar data characteristics select the same members and therefore share statistical strength.
  arXiv  Detail & Related papers  (2021-07-14T14:15:24Z)
• IFedAvg: Interpretable Data-Interoperability for Federated Learning [39.388223565330385]
  In this work, we define and address low interoperability induced by underlying client data inconsistencies in federated learning for tabular data. The proposed method, iFedAvg, builds on federated averaging adding local element-wise affine layers to allow for a personalized and granular understanding of the collaborative learning process. We evaluate iFedAvg using several public benchmarks and a collection of real-world datasets from the 2014 - 2016 West African Ebola epidemic, jointly forming the largest such dataset in the world.
  arXiv  Detail & Related papers  (2021-07-14T09:54:00Z)
• Specialized federated learning using a mixture of experts [0.6974741712647655]
  In federated learning, clients share a global model that has been trained on decentralized local client data. We propose an alternative method to learn a personalized model for each client in a federated setting. Our results show that the mixture of experts model is better suited as a personalized model for devices in these settings.
  arXiv  Detail & Related papers  (2020-10-05T14:43:57Z)
• 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.