paper-with-me

홈 › Papers

Training Deep Neural Networks via Optimization Over Graphs

2017-02-11 · Guo-Qiang Zhang, W. Bastiaan Kleijn

In this work, we propose to train a deep neural network by distributed optimization over a graph. Two nonlinear functions are considered: the rectified linear unit (ReLU) and a linear unit with both lower and upper cutoffs (DCutLU). The problem reformulation over a graph is realized by explicitly representing ReLU or DCutLU using a set of slack variables. We then apply the alternating direction method of multipliers (ADMM) to update the weights of the network layerwise by solving subproblems of the reformulated problem. Empirical results suggest that the ADMM-based method is less sensitive to overfitting than the stochastic gradient descent (SGD) and Adam methods.

📄 PDF Abstract BibTeX arXiv:1702.03380

Code (0)

등록된 구현이 없습니다.

Tasks

Distributed Optimization

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Time

2020-06-06 · Iddo Drori, Anant Kharkar, William R. Sickinger, Brandon Kates 외

Combinatorial optimization algorithms for graph problems are usually designed afresh for each new problem with careful attention by an expert to the problem structure. In this work, we develop a new framework to solve an…

Combinatorial OptimizationGraph Neural NetworkTraveling Salesman Problem

Characterizing and Understanding Distributed GNN Training on GPUs

2022-04-18 · Haiyang Lin, Mingyu Yan, Xiaocheng Yang, Mo Zou 외

Graph neural network (GNN) has been demonstrated to be a powerful model in many domains for its effectiveness in learning over graphs. To scale GNN training for large graphs, a widely adopted approach is distributed trai…

Graph Neural Network

A Distributed Training Architecture For Combinatorial Optimization

2025-11-12 · Yuyao Long arxiv

In recent years, graph neural networks (GNNs) have been widely applied in tackling combinatorial optimization problems. However, existing methods still suffer from limited accuracy when addressing that on complex graphs …

Computational EfficiencyReinforcement Learning

A Unified Pre-training and Adaptation Framework for Combinatorial Optimization on Graphs

2023-12-16 · Ruibin Zeng, Minglong Lei, Lingfeng Niu, Lan Cheng

Combinatorial optimization (CO) on graphs is a classic topic that has been extensively studied across many scientific and industrial fields. Recently, solving CO problems on graphs through learning methods has attracted …

Combinatorial OptimizationDomain Adaptation

Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets

2021-03-01 · Haoran You, Zhihan Lu, Zijian Zhou, Yonggan Fu 외

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art deep learning model for representation learning on graphs. However, it remains notoriously challenging to train and inference GCNs over large graph…

Representation Learning