mlsanityData to 14 Oct 2026

A Systematic Evaluation of Node Embedding Robustness

arXiv 2209.08064 ↗First posted 16 Sep 2022cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Node embedding methods map network nodes to low dimensional vectors that can be subsequently used in a variety of downstream prediction tasks. The popularity of these methods has grown significantly in recent years, yet, their robustness to perturbations of the input data is still poorly understood. In this paper, we assess the empirical robustness of node embedding models to random and adversarial poisoning attacks. Our systematic evaluation covers representative embedding methods based on Skip-Gram, matrix factorization, and deep neural networks. We compare edge addition, deletion and rewiring attacks computed using network properties as well as node labels. We also investigate the performance of popular node classification attack baselines that assume full knowledge of the node labels. We report qualitative results via embedding visualization and quantitative results in terms of downstream node classification and network reconstruction performances. We find that node classification results are impacted more than network reconstruction ones, that degree-based and label-based attacks are on average the most damaging and that label heterophily can strongly influence attack performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 16 Sep 2022.

Builds on

24 of 52 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  6. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  7. 2015LINE: Large-scale Information Network Embeddingcited by 582
  8. 2020Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease predictioncited by 373
  9. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  10. 2018Adversarial Attack on Graph Structured Datacited by 301
  11. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 198
  12. 2019Fake News Detection on Social Media using Geometric Deep Learningcited by 118
12 more
  1. 2020Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attackscited by 116
  2. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  3. 2021Robustness of Graph Neural Networks at Scalecited by 100
  4. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  5. 2018VERSE: Versatile Graph Embeddings from Similarity Measurescited by 54
  6. 2019NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorizationcited by 48
  7. 2021Graph Structural Attack by Perturbing Spectral Distancecited by 16
  8. 2018Conditional Network Embeddingscited by 15
  9. 2020CSNE: Conditional Signed Network Embeddingcited by 4
  10. 2020Neural graph embeddings as explicit low-rank matrix factorization for link predictioncited by 4
  11. 2020Evaluating Graph Vulnerability and Robustness using TIGERcited by 1
  12. 2021Adversarial Robustness of Probabilistic Network Embedding for Link Predictioncited by 1

Built on by

Not cited yet.