Search Results for author:
Found 26 papers, 13 papers with code
TEST_POSITIVE at W-NUT 2020 Shared Task-3: Cross-task modeling
The competition of extracting COVID-19 events from Twitter is to develop systems that can automatically extract related events from tweets.
Extracting COVID-19 Events from Twitter
Language Modeling
+5
Stealing Training Graphs from Graph Neural Networks
As neural networks can memorize the training samples, the model parameters of GNNs have a high risk of leaking private training data.
Trojan Prompt Attacks on Graph Neural Networks
Graph Prompt Learning (GPL) has been introduced as a promising approach that uses prompts to adapt pre-trained GNN models to specific downstream tasks without requiring fine-tuning of the entire model.
Robustness-Inspired Defense Against Backdoor Attacks on Graph Neural Networks
With this observation, we propose using random edge dropping to detect backdoors and theoretically show that it can efficiently distinguish poisoned nodes from clean ones.
Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
To ensure a high attack success rate with ID triggers, we introduce novel modules designed to enhance trigger memorization by the victim model trained on poisoned graph.
PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protection
PreGIP incorporates a task-free watermarking loss to watermark the embedding space of pretrained GNN encoder.
Shape-aware Graph Spectral Learning
Spectral Graph Neural Networks (GNNs) are gaining attention for their ability to surpass the limitations of message-passing GNNs.
Certifiably Robust Graph Contrastive Learning
Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method in providing effective certifiable robustness and enhancing the robustness of any GCL model.
A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs.
Unnoticeable Backdoor Attacks on Graph Neural Networks
In particular, backdoor attack poisons the graph by attaching triggers and the target class label to a set of nodes in the training graph.
HP-GMN: Graph Memory Networks for Heterophilous Graphs
Graph neural networks (GNNs) have achieved great success in various graph problems.
Towards Prototype-Based Self-Explainable Graph Neural Network
Therefore, we study a novel problem of learning prototype-based self-explainable GNNs that can simultaneously give accurate predictions and prototype-based explanations on predictions.
A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
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.
Learning Fair Models without Sensitive Attributes: A Generative Approach
The lack of sensitive attributes challenges many existing fair classifiers.
Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series
Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks.
Ranked #3 on
Anomaly Detection
on voraus-AD
Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels
To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes.
Label-Wise Graph Convolutional Network for Heterophilic Graphs
Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications.
Ranked #1 on
Node Classification
on Crocodile
Towards Self-Explainable Graph Neural Network
Though many efforts are taken to improve the explainability of deep learning, they mainly focus on i. i. d data, which cannot be directly applied to explain the predictions of GNNs because GNNs utilize both node features and graph topology to make predictions.
Labeled Data Generation with Inexact Supervision
We propose a novel generative framework named as ADDES which can synthesize high-quality labeled data for target classification tasks by learning from data with inexact supervision and the relations between inexact supervision and target classes.
NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
Graph Neural Networks (GNNs) have achieved promising results for semi-supervised learning tasks on graphs such as node classification.
Times Series Forecasting for Urban Building Energy Consumption Based on Graph Convolutional Network
After discussion, it is found that data-driven models integrated engineering or physical knowledge can significantly improve the urban building energy simulation.
Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features
Though the sensitive attribute of each data sample is unknown, we observe that there are usually some non-sensitive features in the training data that are highly correlated with sensitive attributes, which can be used to alleviate the bias.
TEST_POSITIVE at W-NUT 2020 Shared Task-3: Joint Event Multi-task Learning for Slot Filling in Noisy Text
The competition of extracting COVID-19 events from Twitter is to develop systems that can automatically extract related events from tweets.
Extracting COVID-19 Events from Twitter
Language Modeling
+6
Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
Though extensive studies of fair classification have been conducted on i. i. d data, methods to address the problem of discrimination on non-i. i. d data are rather limited.
Ginger Cannot Cure Cancer: Battling Fake Health News with a Comprehensive Data Repository
Nowadays, Internet is a primary source of attaining health information.
Unsupervised Image Super-Resolution with an Indirect Supervised Path
The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image.
