paper-with-me

홈 › Papers

Implicit Regularization of Mini-Batch Training in Graph Neural Networks

2026-05-21 · Clement Wang, Antoine Vialle, Robin Vaysse, Thomas Bonald arxiv

Mini-batch training of Graph Neural Networks (GNNs) is fundamentally different from training on i.i.d. data: sampling a subgraph alters the topology and introduces boundary effects, leading prior work to develop structure-aware samplers that preserve local connectivity and reduce embedding variance. Surprisingly, we demonstrate that the simplest possible scheme, Random Node Sampling (RNS), training on the induced subgraph of uniformly sampled nodes, matches or outperforms full-graph training on 8 of 10 datasets at a fraction of the wall-clock time and memory. To explain this, we apply backward error analysis to graph mini-batch Stochastic Gradient Descent (SGD) and show that it implicitly minimizes the sampled loss plus a regularizer proportional to the mini-batch gradient variance, a quantity directly shaped by the sampler. Although RNS discards local structure, it produces mini-batches whose expected loss is closer to the full-graph loss, and whose per-batch gradients have lower variance, yielding a better implicit objective. Our analysis reframes the choice of graph sampler as a form of implicit regularization, and identifies RNS as a strong, theoretically grounded method for scalable GNN training.

📄 PDF Abstract BibTeX arXiv:2605.22480

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Implicit Gradient Alignment in Distributed and Federated Learning

2021-06-25 · Yatin Dandi, Luis Barba, Martin Jaggi

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In t…

Federated Learning

How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD

2024-06-17 · Pierfrancesco Beneventano, Andrea Pinto, Tomaso Poggio

We investigate the ability of deep neural networks to identify the support of the target function. Our findings reveal that mini-batch SGD effectively learns the support in the first layer of the network by shrinking to …

On the Origin of Implicit Regularization in Stochastic Gradient Descent

2021-01-28 · ICLR 2021 1 · Samuel L. Smith, Benoit Dherin, David G. T. Barrett, Soham De

For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this …

Disentangling the Mechanisms Behind Implicit Regularization in SGD

2022-11-29 · Zachary Novack, Simran Kaur, Tanya Marwah, Saurabh Garg 외

A number of competing hypotheses have been proposed to explain why small-batch Stochastic Gradient Descent (SGD)leads to improved generalization over the full-batch regime, with recent work crediting the implicit regular…

Hyperparameter Tuning and Implicit Regularization in Minibatch SGD

2019-09-25 · Samuel L Smith, Erich Elsen, Soham De

This paper makes two contributions towards understanding how the hyperparameters of stochastic gradient descent affect the final training loss and test accuracy of neural networks. First, we argue that stochastic gradien…