Personalized Decentralized Multi-Task Learning Over Dynamic
Communication Graphs
- URL: http://arxiv.org/abs/2212.11268v1
- Date: Wed, 21 Dec 2022 18:58:24 GMT
- Title: Personalized Decentralized Multi-Task Learning Over Dynamic
Communication Graphs
- Authors: Matin Mortaheb and Sennur Ulukus
- Abstract summary: We propose a decentralized and federated learning algorithm for tasks that are positively and negatively correlated.
Our algorithm uses gradients to calculate the correlations among tasks automatically, and dynamically adjusts the communication graph to connect mutually beneficial tasks and isolate those that may negatively impact each other.
We conduct experiments on a synthetic Gaussian dataset and a large-scale celebrity attributes (CelebA) dataset.
- Score: 59.96266198512243
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Decentralized and federated learning algorithms face data heterogeneity as
one of the biggest challenges, especially when users want to learn a specific
task. Even when personalized headers are used concatenated to a shared network
(PF-MTL), aggregating all the networks with a decentralized algorithm can
result in performance degradation as a result of heterogeneity in the data. Our
algorithm uses exchanged gradients to calculate the correlations among tasks
automatically, and dynamically adjusts the communication graph to connect
mutually beneficial tasks and isolate those that may negatively impact each
other. This algorithm improves the learning performance and leads to faster
convergence compared to the case where all clients are connected to each other
regardless of their correlations. We conduct experiments on a synthetic
Gaussian dataset and a large-scale celebrity attributes (CelebA) dataset. The
experiment with the synthetic data illustrates that our proposed method is
capable of detecting tasks that are positively and negatively correlated.
Moreover, the results of the experiments with CelebA demonstrate that the
proposed method may produce significantly faster training results than
fully-connected networks.
Related papers
- FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup
for Non-IID Data [54.81695390763957]
Federated learning is an emerging distributed machine learning method.
We propose a heterogeneous local variant of AMSGrad, named FedLALR, in which each client adjusts its learning rate.
We show that our client-specified auto-tuned learning rate scheduling can converge and achieve linear speedup with respect to the number of clients.
arXiv Detail & Related papers (2023-09-18T12:35:05Z) - FedGradNorm: Personalized Federated Gradient-Normalized Multi-Task
Learning [50.756991828015316]
Multi-task learning (MTL) is a novel framework to learn several tasks simultaneously with a single shared network.
We propose FedGradNorm which uses a dynamic-weighting method to normalize norms in order to balance learning speeds among different tasks.
arXiv Detail & Related papers (2022-03-24T17:43:12Z) - Resource-constrained Federated Edge Learning with Heterogeneous Data:
Formulation and Analysis [8.863089484787835]
We propose a distributed approximate Newton-type Newton-type training scheme, namely FedOVA, to solve the heterogeneous statistical challenge brought by heterogeneous data.
FedOVA decomposes a multi-class classification problem into more straightforward binary classification problems and then combines their respective outputs using ensemble learning.
arXiv Detail & Related papers (2021-10-14T17:35:24Z) - Exploiting Shared Representations for Personalized Federated Learning [54.65133770989836]
We propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client.
Our algorithm harnesses the distributed computational power across clients to perform many local-updates with respect to the low-dimensional local parameters for every update of the representation.
This result is of interest beyond federated learning to a broad class of problems in which we aim to learn a shared low-dimensional representation among data distributions.
arXiv Detail & Related papers (2021-02-14T05:36:25Z) - Straggler-Resilient Federated Learning: Leveraging the Interplay Between
Statistical Accuracy and System Heterogeneity [57.275753974812666]
Federated learning involves learning from data samples distributed across a network of clients while the data remains local.
In this paper, we propose a novel straggler-resilient federated learning method that incorporates statistical characteristics of the clients' data to adaptively select the clients in order to speed up the learning procedure.
arXiv Detail & Related papers (2020-12-28T19:21:14Z) - A Theoretical Perspective on Differentially Private Federated Multi-task
Learning [12.935153199667987]
collaborative learning models need to be developed with respect to both privacy and utility concerns.
We propose a new federated multi-task for effective parameter transfer differential privacy to protect at the client level.
We are the first to provide both privacy utility guarantees for such a proposed algorithm.
arXiv Detail & Related papers (2020-11-14T00:53:16Z) - Mining Implicit Entity Preference from User-Item Interaction Data for
Knowledge Graph Completion via Adversarial Learning [82.46332224556257]
We propose a novel adversarial learning approach by leveraging user interaction data for the Knowledge Graph Completion task.
Our generator is isolated from user interaction data, and serves to improve the performance of the discriminator.
To discover implicit entity preference of users, we design an elaborate collaborative learning algorithms based on graph neural networks.
arXiv Detail & Related papers (2020-03-28T05:47:33Z)
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.