Recent Advances in Reliable Deep Graph Learning: Adversarial Attack, Inherent Noise, and Distribution Shift

Wu, Bingzhe; Li, Jintang; Hou, Chengbin; Fu, Guoji; Bian, Yatao; Chen, Liang; Huang, Junzhou

doi:10.48550/arxiv.2202.07114

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in real-world scenarios, distribution shifts, such as covariate shifts, frequently occur between the labeled training set and the unlabeled testing set [32]. As a result, a GNN classifier may overfit to the irregularities of the training data, adversely affecting its performance post-deployment.…”

Section: Distribution Shifts On Graphsmentioning

confidence: 99%

Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels

Wang,

Zhao,

Wang

2024

Proceedings of the 17th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Few-shot node classification poses a significant challenge for Graph Neural Networks (GNNs) due to insufficient supervision and potential distribution shifts between labeled and unlabeled nodes. Self-training has emerged as a widely popular framework to leverage the abundance of unlabeled data, which expands the training set by assigning pseudo-labels to selected unlabeled nodes. Efforts have been made to develop various selection strategies based on confidence, information gain, etc. However, none of these methods takes into account the distribution shift between the training and testing node sets. The pseudo-labeling step may amplify this shift and even introduce new ones, hindering the effectiveness of self-training. Therefore, in this work, we explore the potential of explicitly bridging the distribution shift between the expanded training set and test set during self-training. To this end, we propose a novel Distribution-Consistent Graph Self-Training (DC-GST) framework to identify pseudo-labeled nodes that both are informative and capable of redeeming the distribution discrepancy and formulate it as a differentiable optimization task. A distributionshift-aware edge predictor is further adopted to augment the graph and increase the model's generalizability in assigning pseudo labels. We evaluate our proposed method on four publicly available benchmark datasets and extensive experiments demonstrate that our framework consistently outperforms state-of-the-art baselines. CCS CONCEPTS• Computing methodologies → Semi-supervised learning settings; Neural networks.

show abstract

Section: Distribution Shifts On Graphsmentioning

confidence: 99%

Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels

Wang,

Zhao,

Wang

2024

Proceedings of the 17th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…There exist works aiming to estimate the uncertainty [48] for time series forecasting [71,96,36] by epistemic uncertainty. Nevertheless, the inevitable aleatoric uncertainty of time series is often ignored, which may stem from error-prone data measurement, collection, and so forth [97]. Another line of studies focuses on detecting noise in time series data [66] or devising suitable models for noise alleviation [33].…”

Section: A3 Uncertainty Estimation and Denoising For Time Series Fore...mentioning

confidence: 99%

Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement

Li¹,

Lu²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Time series forecasting has been a widely explored task of great importance in many applications. However, it is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder (BVAE) equipped with diffusion, denoise, and disentanglement, namely D 3 VAE. Specifically, a coupled diffusion probabilistic model is proposed to augment the time series data without increasing the aleatoric uncertainty and implement a more tractable inference process with BVAE. To ensure the generated series move toward the true target, we further propose to adapt and integrate the multiscale denoising score matching into the diffusion process for time series forecasting. In addition, to enhance the interpretability and stability of the prediction, we treat the latent variable in a multivariate manner and disentangle them on top of minimizing total correlation. Extensive experiments on synthetic and real-world data show that D 3 VAE outperforms competitive algorithms with remarkable margins. Our implementation is available at https://github.com/ PaddlePaddle/PaddleSpatial/tree/main/research/D3VAE.

show abstract

“…Hence, developing robust GNNs is another important aspect of trustworthiness and many efforts have been taken. There are already several comprehensive surveys about adversarial attacks and defenses on graphs [29,87,171,197]. Therefore, in this section, we briefly give the overview of adversarial learning on graphs, but focus more on methods in emerging directions such as scalable attacks, graph backdoor attacks, and recent defense methods.…”

Section: Robustness Of Graph Neural Networkmentioning

confidence: 99%

“…Fair GNNs [35] and explainable GNNs [36,216] also become hot topics to address the concerns in trustworthiness. There are several surveys of GNNs in robustness [87,171,197,243] and explainability [221]. However, none of them thoroughly discuss about the trustworthiness of GNNs, which should also cover the dimensions of privacy and fairness.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

Dai¹,

Zhao²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have made rapid developments in the recent years. Due to their great ability in modeling graph-structured data, GNNs are vastly used in various applications, including high-stakes scenarios such as financial analysis, traffic predictions, and drug discovery. Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society. For example, existing works demonstrate that attackers can fool the GNNs to give the outcome they desire with unnoticeable perturbation on training graph. GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias. Consequently, trustworthy GNNs in various aspects are emerging to prevent the harm from GNN models and increase the users' trust in GNNs. In this paper, we give a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability. For each aspect, we give the taxonomy of the related methods and formulate the general frameworks for the multiple categories of trustworthy GNNs. We also discuss the future research directions of each aspect and connections between these aspects to help achieve trustworthiness.

show abstract

Recent Advances in Reliable Deep Graph Learning: Adversarial Attack, Inherent Noise, and Distribution Shift

Cited by 3 publications

References 0 publications

Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels

Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels

Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

Contact Info

Product

Resources

About