Distributed Learning over Networks with Graph-Attention-Based
Personalization
- URL: http://arxiv.org/abs/2305.13041v1
- Date: Mon, 22 May 2023 13:48:30 GMT
- Title: Distributed Learning over Networks with Graph-Attention-Based
Personalization
- Authors: Zhuojun Tian, Zhaoyang Zhang, Zhaohui Yang, Richeng Jin and Huaiyu Dai
- Abstract summary: We propose a graph-based personalized algorithm (GATTA) for distributed deep learning.
In particular, the personalized model in each agent is composed of a global part and a node-specific part.
By treating each agent as one node in a graph the node-specific parameters as its features, the benefits of the graph attention mechanism can be inherited.
- Score: 49.90052709285814
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In conventional distributed learning over a network, multiple agents
collaboratively build a common machine learning model. However, due to the
underlying non-i.i.d. data distribution among agents, the unified learning
model becomes inefficient for each agent to process its locally accessible
data. To address this problem, we propose a graph-attention-based personalized
training algorithm (GATTA) for distributed deep learning. The GATTA enables
each agent to train its local personalized model while exploiting its
correlation with neighboring nodes and utilizing their useful information for
aggregation. In particular, the personalized model in each agent is composed of
a global part and a node-specific part. By treating each agent as one node in a
graph and the node-specific parameters as its features, the benefits of the
graph attention mechanism can be inherited. Namely, instead of aggregation
based on averaging, it learns the specific weights for different neighboring
nodes without requiring prior knowledge about the graph structure or the
neighboring nodes' data distribution. Furthermore, relying on the
weight-learning procedure, we develop a communication-efficient GATTA by
skipping the transmission of information with small aggregation weights.
Additionally, we theoretically analyze the convergence properties of GATTA for
non-convex loss functions. Numerical results validate the excellent
performances of the proposed algorithms in terms of convergence and
communication cost.
Related papers
- Self-Supervised Contrastive Graph Clustering Network via Structural Information Fusion [15.293684479404092]
We propose a novel deep graph clustering method called CGCN.
Our approach introduces contrastive signals and deep structural information into the pre-training process.
Our method has been experimentally validated on multiple real-world graph datasets.
arXiv Detail & Related papers (2024-08-08T09:49:26Z) - Personalized Decentralized Multi-Task Learning Over Dynamic
Communication Graphs [59.96266198512243]
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.
arXiv Detail & Related papers (2022-12-21T18:58:24Z) - GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton.
The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases.
In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
arXiv Detail & Related papers (2022-12-01T11:49:07Z) - Neighborhood Convolutional Network: A New Paradigm of Graph Neural
Networks for Node Classification [12.062421384484812]
Graph Convolutional Network (GCN) decouples neighborhood aggregation and feature transformation in each convolutional layer.
In this paper, we propose a new paradigm of GCN, termed Neighborhood Convolutional Network (NCN)
In this way, the model could inherit the merit of decoupled GCN for aggregating neighborhood information, at the same time, develop much more powerful feature learning modules.
arXiv Detail & Related papers (2022-11-15T02:02:51Z) - Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
Modelling long-range dependencies is critical for scene understanding tasks in computer vision.
A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive.
We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
arXiv Detail & Related papers (2022-09-20T14:41:37Z) - Network Gradient Descent Algorithm for Decentralized Federated Learning [0.2867517731896504]
We study a fully decentralized federated learning algorithm, which is a novel descent gradient algorithm executed on a communication-based network.
In the NGD method, only statistics (e.g., parameter estimates) need to be communicated, minimizing the risk of privacy.
We find that both the learning rate and the network structure play significant roles in determining the NGD estimator's statistical efficiency.
arXiv Detail & Related papers (2022-05-06T02:53:31Z) - Graph Ordering Attention Networks [22.468776559433614]
Graph Neural Networks (GNNs) have been successfully used in many problems involving graph-structured data.
We introduce the Graph Ordering Attention (GOAT) layer, a novel GNN component that captures interactions between nodes in a neighborhood.
GOAT layer demonstrates its increased performance in modeling graph metrics that capture complex information.
arXiv Detail & Related papers (2022-04-11T18:13:19Z) - Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised
Node Classification [59.06717774425588]
We propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field.
It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations.
We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.
arXiv Detail & Related papers (2021-07-27T19:47:53Z) - Pre-Trained Models for Heterogeneous Information Networks [57.78194356302626]
We propose a self-supervised pre-training and fine-tuning framework, PF-HIN, to capture the features of a heterogeneous information network.
PF-HIN consistently and significantly outperforms state-of-the-art alternatives on each of these tasks, on four datasets.
arXiv Detail & Related papers (2020-07-07T03:36:28Z)
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.