Pre-Training Graph Neural Networks for Data-Efficient Brain Network Analysis

Attention-enhanced Deep Learning Models for Data Cleaning and Integration

Computational Structures as Neural Symbolic Representation

Enhancing Document Understanding through the Incorporation of Structural Inference

Interpretable and Interactive Representation Learning on Geometric Data

Synthetic Trajectory Generation via Clustering-Based Semi-supervised Generative Adversarial Networks

The Applications of Alternating Minimization Algorithms on Deep Learning Models

Improving Interactive Search with User Feedback

Towards the Robustness of Deep Learning Systems Against Adversarial Examples in Sequential Data