Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration Learning
Dec 6, 2021
Speakers
Hongrui Liu
Speaker · 0 followers
Cheng Yang
Speaker · 0 followers
About
Despite Graph Neural Networks (GNNs) have achieved remarkable accuracy, whether the results are trustworthy is still unexplored. Previous studies suggest that many modern neural networks are over-confident on the predictions, however, surprisingly, we discover that GNNs are primarily in the opposite direction, i.e., GNNs are under-confident. Therefore, the confidence calibration for GNNs is highly desired. In this paper, we propose a novel trustworthy GNN model by designing a topology-aware post-hoc calibration function. Specifically, we first verify that the confidence distribution in a graph has homophily property, and this finding inspires us to design a calibration GNN model (CaGCN) to learn the calibration function. CaGCN is able to obtain a unique transformation from logits of GNNs to the calibrated confidence for each node, meanwhile, such transformation is able to preserve the order between classes, satisfying the accuracy-preserving property. Moreover, we apply the calibration GNN to self-training framework, showing that more trustworthy pseudo labels can be obtained with the calibrated confidence and further improve the performance. Extensive experiments demonstrate the effectiveness of our proposed model in terms of both calibration and accuracy.Despite Graph Neural Networks (GNNs) have achieved remarkable accuracy, whether the results are trustworthy is still unexplored. Previous studies suggest that many modern neural networks are over-confident on the predictions, however, surprisingly, we discover that GNNs are primarily in the opposite direction, i.e., GNNs are under-confident. Therefore, the confidence calibration for GNNs is highly desired. In this paper, we propose a novel trustworthy GNN model by designing a topology-aware post…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Symmetry Discovery with Deep Learning
Watch later
Krish Desai, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
MathBERT:A Pre-trained Language Model for General NLP Tasks in Mathematics Education
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Seasons in Drift: A Long Term Thermal Imaging Dataset for Studying Concept Drift
Watch later
Ivan Nikolov, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Reflective Explorer: Online Meta-Exploration from Offline Data in Realistic Robotic Tasks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Live Intro
Watch later
Felipe Tobar, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%