paper-with-me

Papers

Using Random Noise Equivariantly to Boost Graph Neural Networks Universally

2025-02-04 · Xiyuan Wang, Muhan Zhang

Recent advances in Graph Neural Networks (GNNs) have explored the potential of random noise as an input feature to enhance expressivity across diverse tasks. However, naively incorporating noise can degrade performance, while architectures tailored to exploit noise for specific tasks excel yet lack broad applicability. This paper tackles these issues by laying down a theoretical framework that elucidates the increased sample complexity when introducing random noise into GNNs without careful design. We further propose Equivariant Noise GNN (ENGNN), a novel architecture that harnesses the symmetrical properties of noise to mitigate sample complexity and bolster generalization. Our experiments demonstrate that using noise equivariantly significantly enhances performance on node-level, link-level, subgraph, and graph-level tasks and achieves comparable performance to models designed for specific tasks, thereby offering a general method to boost expressivity across various graph tasks.

📄 PDF Abstract BibTeX arXiv:2502.02479

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence

2024-07-20 · Shuya Feng, Meisam Mohammady, Hanbin Hong, Shenao Yan 외

Differentially private federated learning (DP-FL) is a promising technique for collaborative model training while ensuring provable privacy for clients. However, optimizing the tradeoff between privacy and accuracy remai…

Federated Learning

Non-Convex Boosting Overcomes Random Label Noise

2014-09-09 · Sunsern Cheamanunkul, Evan Ettinger, Yoav Freund

The sensitivity of Adaboost to random label noise is a well-studied problem. LogitBoost, BrownBoost and RobustBoost are boosting algorithms claimed to be less sensitive to noise than AdaBoost. We present the results of e…

Sensitivity

UniCR: Universally Approximated Certified Robustness via Randomized Smoothing

2022-07-05 · Hanbin Hong, Binghui Wang, Yuan Hong

We study certified robustness of machine learning classifiers against adversarial perturbations. In particular, we propose the first universally approximated certified robustness (UniCR) framework, which can approximate …

Boosting in the Presence of Massart Noise

2021-06-14 · Ilias Diakonikolas, Russell Impagliazzo, Daniel Kane, Rex Lei 외

We study the problem of boosting the accuracy of a weak learner in the (distribution-independent) PAC model with Massart noise. In the Massart noise model, the label of each example $x$ is independently misclassified wit…

Strongly universally consistent nonparametric regression and classification with privatised data

2020-10-31 · Thomas Berrett, László Györfi, Harro Walk

In this paper we revisit the classical problem of nonparametric regression, but impose local differential privacy constraints. Under such constraints, the raw data $(X_1,Y_1),\ldots,(X_n,Y_n)$, taking values in $\mathbb{…

Binary ClassificationGeneral Classificationregression