1 code implementation • 26 Apr 2024 • Cheng Ding, Zhicheng Guo, Zhaoliang Chen, Randall J Lee, Cynthia Rudin, Xiao Hu
However, large foundation models are typically trained on high-quality data, which poses a significant challenge, given the prevalence of poor-quality real-world data.
no code implementations • 1 Apr 2024 • Chen Yang, Junzhuo Li, Xinyao Niu, Xinrun Du, Songyang Gao, Haoran Zhang, Zhaoliang Chen, Xingwei Qu, Ruibin Yuan, Yizhi Li, Jiaheng Liu, Stephen W. Huang, Shawn Yue, Wenhu Chen, Jie Fu, Ge Zhang
To address the aforementioned limitations, this paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints.
no code implementations • 14 Mar 2024 • Zhaoliang Chen, Zhihao Wu, Ylli Sadikaj, Claudia Plant, Hong-Ning Dai, Shiping Wang, Wenzhong Guo
Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method.
no code implementations • 14 Apr 2023 • Zhaoliang Chen, Zhihao Wu, Zhenghong Lin, Shiping Wang, Claudia Plant, Wenzhong Guo
In light of this, we propose an Alternating Graph-regularized Neural Network (AGNN) composed of Graph Convolutional Layer (GCL) and Graph Embedding Layer (GEL).
no code implementations • 13 Apr 2023 • Zhaoliang Chen, Zhihao Wu, Luying Zhong, Claudia Plant, Shiping Wang, Wenzhong Guo
Heterogeneous graph neural networks aim to discover discriminative node embeddings and relations from multi-relational networks. One challenge of heterogeneous graph learning is the design of learnable meta-paths, which significantly influences the quality of learned embeddings. Thus, in this paper, we propose an Attributed Multi-Order Graph Convolutional Network (AMOGCN), which automatically studies meta-paths containing multi-hop neighbors from an adaptive aggregation of multi-order adjacency matrices.
no code implementations • 9 Dec 2022 • Zhaoliang Chen, Lele Fu, Shunxin Xiao, Shiping Wang, Claudia Plant, Wenzhong Guo
Due to the powerful capability to gather information of neighborhood nodes, in this paper, we apply Graph Convolutional Network (GCN) to cope with heterogeneous-graph data originating from multi-view data, which is still under-explored in the field of GCN.
no code implementations • 16 Nov 2022 • Zhaoliang Chen, Lele Fu, Jie Yao, Wenzhong Guo, Claudia Plant, Shiping Wang
In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms.