paper-with-me

홈 › Papers

Revisiting Robustness in Graph Machine Learning

2023-05-01 · Lukas Gosch, Daniel Sturm, Simon Geisler, Stephan Günnemann

Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results uncover: $i)$ for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption; $ii)$ surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs significantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node.

📄 PDF Abstract BibTeX arXiv:2305.00851

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

Test 설명 없음
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models

2021-10-24 · WNUT (ACL) 2021 11 · José Carlos Rosales Núñez, Guillaume Wisniewski, Djamé Seddah

This work explores the capacities of character-based Neural Machine Translation to translate noisy User-Generated Content (UGC) with a strong focus on exploring the limits of such approaches to handle productive UGC phen…

Machine TranslationTranslation

The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations

2024-07-19 · Tyler LaBonte, John C. Hill, Xinchen Zhang, Vidya Muthukumar 외

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned mod…

Revisiting Graph Neural Networks: All We Have is Low-Pass Filters

2019-05-23 · Hoang NT, Takanori Maehara

Graph neural networks have become one of the most important techniques to solve machine learning problems on graph-structured data. Recent work on vertex classification proposed deep and distributed learning models to ac…

AllGeneral ClassificationGraph Neural Network

Revisiting FastMap: New Applications

2025-03-14 · Ang Li

FastMap was first introduced in the Data Mining community for generating Euclidean embeddings of complex objects. In this dissertation, we first present FastMap to generate Euclidean embeddings of graphs in near-linear t…

Community Detection

Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces

2022-11-01 · Ashish Tiwari, Sresth Tosniwal, Shanmuganathan Raman

Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have sole…

Node Classification