1 code implementation • 14 Feb 2024 • Linfeng Cao, Haoran Deng, Yang Yang, Chunping Wang, Lei Chen
In this paper, we argue that properly fetching and condensing the background nodes from massive web graph data might be a more economical shortcut to tackle the obstacles fundamentally.
no code implementations • 3 Feb 2024 • Xuanwen Huang, Wei Chow, Yang Wang, Ziwei Chai, Chunping Wang, Lei Chen, Yang Yang
Extensive experiments on eight untrained graphs demonstrate that DyExpert achieves state-of-the-art performance in cross-domain link prediction.
1 code implementation • 21 Dec 2023 • Yifei Sun, Qi Zhu, Yang Yang, Chunping Wang, Tianyu Fan, Jiajun Zhu, Lei Chen
In this paper, we identify the fundamental cause of structural divergence as the discrepancy of generative patterns between the pre-training and downstream graphs.
1 code implementation • 20 Dec 2023 • Chenglu Pan, Jiarong Xu, Yue Yu, Ziqi Yang, Qingbiao Wu, Chunping Wang, Lei Chen, Yang Yang
Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.
1 code implementation • NeurIPS 2023 • Jiarong Xu, Renhong Huang, Xin Jiang, Yuxuan Cao, Carl Yang, Chunping Wang, Yang Yang
The proposed pre-training pipeline is called the data-active graph pre-training (APT) framework, and is composed of a graph selector and a pre-training model.
1 code implementation • ICCV 2023 • Lin Li, Guikun Chen, Jun Xiao, Yi Yang, Chunping Wang, Long Chen
Specifically, we first decompose each relation triplet feature into two components: intrinsic feature and extrinsic feature, which correspond to the intrinsic characteristics and extrinsic contexts of a relation triplet, respectively.
1 code implementation • 29 Mar 2023 • Yuxuan Cao, Jiarong Xu, Carl Yang, Jiaan Wang, Yunchao Zhang, Chunping Wang, Lei Chen, Yang Yang
All convex combinations of graphon bases give rise to a generator space, from which graphs generated form the solution space for those downstream data that can benefit from pre-training.
1 code implementation • NeurIPS 2023 • Taoran Fang, Yunchao Zhang, Yang Yang, Chunping Wang, Lei Chen
In this paper, we introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy.
no code implementations • 30 Jun 2022 • Xuanwen Huang, Yang Yang, Yang Wang, Chunping Wang, Zhisheng Zhang, Jiarong Xu, Lei Chen, Michalis Vazirgiannis
Since GAD emphasizes the application and the rarity of anomalous samples, enriching the varieties of its datasets is fundamental work.
2 code implementations • 21 Apr 2022 • Taoran Fang, Zhiqing Xiao, Chunping Wang, Jiarong Xu, Xuan Yang, Yang Yang
First, it is challenging to find a universal method that are suitable for all cases considering the divergence of different datasets and models.
no code implementations • 12 Dec 2020 • Jiarong Xu, Yizhou Sun, Xin Jiang, Yanhao Wang, Yang Yang, Chunping Wang, Jiangang Lu
To bridge the gap between theoretical graph attacks and real-world scenarios, in this work, we propose a novel and more realistic setting: strict black-box graph attack, in which the attacker has no knowledge about the victim model at all and is not allowed to send any queries.
no code implementations • 4 Dec 2020 • Jiarong Xu, Yang Yang, Junru Chen, Chunping Wang, Xin Jiang, Jiangang Lu, Yizhou Sun
Additionally, we explore a provable connection between the robustness of the unsupervised graph encoder and that of models on downstream tasks.
1 code implementation • 30 Apr 2019 • Rui Feng, Yang Yang, Yuehan Lyu, Chenhao Tan, Yizhou Sun, Chunping Wang
Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval.
no code implementations • 28 Nov 2018 • Jiangyi Liu, Chunping Wang, Wei Wang
Most multi-target tracking filters assume that one target and its observation follow a Hidden Markov Chain (HMC) model, but the implicit independence assumption of HMC model is invalid in many practical applications, and a Pairwise Markov Chain (PMC) model is more universally suitable than traditional HMC model.