78 citations · 135 across the 16 of their papers we have counts for
8 papers · 1 filter
Domain Generalization Deep Graph Transformation
Shiyu Wang, Guangji Bai, Qingyang Zhu +2
Graph transformation that predicts graph transition from one mode to another is an important and common problem. Despite much progress in developing advanced graph transformation t…
Saliency-Augmented Memory Completion for Continual Learning
Guangji Bai, Chen Ling, Yuyang Gao +1
Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic…
Multi-objective Deep Data Generation with Correlated Property Control
Shiyu Wang, Xiaojie Guo, Xuanyang Lin +11
Developing deep generative models has been an emerging field due to the ability to model and generate complex data for various purposes, such as image synthesis and molecular desig…
Controllable Data Generation by Deep Learning: A Review
Shiyu Wang, Yuanqi Du, Xiaojie Guo +3
Designing and generating new data under targeted properties has been attracting various critical applications such as molecule design, image editing and speech synthesis. Tradition…
Interpretable Molecular Graph Generation via Monotonic Constraints
Yuanqi Du, Xiaojie Guo, Amarda Shehu +1
Designing molecules with specific properties is a long-lasting research problem and is central to advancing crucial domains such as drug discovery and material science. Recent adva…
Disentangled Spatiotemporal Graph Generative Models
Yuanqi Du, Xiaojie Guo, Hengning Cao +2
Spatiotemporal graph represents a crucial data structure where the nodes and edges are embedded in a geometric space and can evolve dynamically over time. Nowadays, spatiotemporal…
Black-box Node Injection Attack for Graph Neural Networks
Mingxuan Ju, Yujie Fan, Yanfang Ye +1
Graph Neural Networks (GNNs) have drawn significant attentions over the years and been broadly applied to vital fields that require high security standard such as product recommend…
DT-LET: Deep Transfer Learning by Exploring where to Transfer
Jianzhe Lin, Qi Wang, Rabab Ward +1
Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains. This…