3 code implementations • NeurIPS 2020 • Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, Xiang Zhang
The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to a lack of generalizability and hindering it from being used in the inductive setting.
1 code implementation • 13 Nov 2020 • Dongsheng Luo, Wei Cheng, Wenchao Yu, Bo Zong, Jingchao Ni, Haifeng Chen, Xiang Zhang
Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics.
1 code implementation • 16 Jan 2024 • Zichuan Liu, Yingying Zhang, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang, Chunlin Chen, Lunting Fan, Qingsong Wen
Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns.
1 code implementation • 4 Jul 2023 • Dongsheng Luo, Yuchen Bian, Yaowei Yan, Xiong Yu, Jun Huan, Xiao Liu, Xiang Zhang
To take advantage of rich information in multiple networks and make better inferences on entities, in this study, we propose random walk on multiple networks, RWM.
1 code implementation • 21 Mar 2023 • Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Yanchi Liu, Yuncong Chen, Haifeng Chen, Xiang Zhang
A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples, such that an encoder can be trained to learn robust and discriminative representations.
1 code implementation • 26 Mar 2021 • Dongsheng Luo, Wei Cheng, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Bo Zong, Yanchi Liu, Zhengzhang Chen, Dongjin Song, Haifeng Chen, Xiang Zhang
We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner.
1 code implementation • 16 Feb 2024 • Xu Zheng, Tianchun Wang, Wei Cheng, Aitian Ma, Haifeng Chen, Mo Sha, Dongsheng Luo
In this study, we address this gap by analyzing time series data augmentation using information theory and summarizing the most commonly adopted augmentations in a unified format.
1 code implementation • 3 Oct 2023 • Xu Zheng, Farhad Shirani, Tianchun Wang, Wei Cheng, Zhuomin Chen, Haifeng Chen, Hua Wei, Dongsheng Luo
An explanation function for GNNs takes a pre-trained GNN along with a graph as input, to produce a `sufficient statistic' subgraph with respect to the graph label.
1 code implementation • 26 Oct 2022 • Tianchun Wang, Wei Cheng, Dongsheng Luo, Wenchao Yu, Jingchao Ni, Liang Tong, Haifeng Chen, Xiang Zhang
Personalized Federated Learning (PFL) which collaboratively trains a federated model while considering local clients under privacy constraints has attracted much attention.
1 code implementation • 15 Jul 2023 • Jiaxing Zhang, Dongsheng Luo, Hua Wei
Driven by the generalized GIB, we propose a graph mixup method, MixupExplainer, with a theoretical guarantee to resolve the distribution shifting issue.
1 code implementation • 9 Nov 2020 • Dongsheng Luo, Yuchen Bian, Xiang Zhang, Jun Huan
Social recommendation system is to predict unobserved user-item rating values by taking advantage of user-user social relation and user-item ratings.
no code implementations • 29 Sep 2021 • Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Yanchi Liu, Haifeng Chen, Xiang Zhang
How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question.
no code implementations • NeurIPS 2021 • Dongkuan Xu, Wei Cheng, Dongsheng Luo, Haifeng Chen, Xiang Zhang
The key point of this framework is to follow the Information Bottleneck principle to reduce the mutual information between contrastive parts while keeping task-relevant information intact at both the levels of the individual module and the entire framework so that the information loss during graph representation learning can be minimized.
no code implementations • 27 May 2022 • Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang
Two typical reasons of spurious explanations are identified: confounding effect of latent variables like distribution shift, and causal factors distinct from the original input.
no code implementations • 16 Dec 2022 • Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang
To address this problem, we propose a new framework {\method} and design (1 a topology extractor, which automatically identifies the topology group for each instance with explicit memory cells, (2 a training modulator, which modulates the learning process of the target GNN model to prevent the case of topology-group-wise under-representation.
no code implementations • 7 Jan 2023 • Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang
Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making predictions.
no code implementations • 21 May 2023 • Huaisheng Zhu, Dongsheng Luo, Xianfeng Tang, Junjie Xu, Hui Liu, Suhang Wang
Directly adopting existing post-hoc explainers for explaining link prediction is sub-optimal because: (i) post-hoc explainers usually adopt another strategy or model to explain a target model, which could misinterpret the target model; and (ii) GNN explainers for node classification identify crucial subgraphs around each node for the explanation; while for link prediction, one needs to explain the prediction for each pair of nodes based on graph structure and node attributes.
no code implementations • 15 Jul 2023 • Jiaxing Zhang, Zhuomin Chen, Hao Mei, Dongsheng Luo, Hua Wei
Graph regression is a fundamental task and has received increasing attention in a wide range of graph learning tasks.
no code implementations • 16 Oct 2023 • Junjie Xu, Enyan Dai, Dongsheng Luo, Xiang Zhang, Suhang Wang
Spectral Graph Neural Networks (GNNs) are gaining attention because they can surpass the limitations of message-passing GNNs by learning spectral filters that capture essential frequency information in graph data through task supervision.
no code implementations • 12 Oct 2023 • Minghao Lin, Minghao Cheng, Dongsheng Luo, Yueqi Chen
In our experiment, using GSExtract, we are only able to decode 2. 1\% satellite streams we eavesdropped on in Asia.
no code implementations • 25 Oct 2023 • Tianchun Wang, Dongsheng Luo, Wei Cheng, Haifeng Chen, Xiang Zhang
Dynamic GNNs, with their ever-evolving graph structures, pose a unique challenge and require additional efforts to effectively capture temporal dependencies and structural relationships.
no code implementations • 9 Dec 2023 • Rundong Huang, Farhad Shirani, Dongsheng Luo
Instead, we argue that a modified GIB principle may be used to avoid the aforementioned trivial solutions.
no code implementations • 31 Jan 2024 • Qianying Ren, Dongsheng Luo, Dongjin Song
Recently, various contrastive learning techniques have been developed to categorize time series data and exhibit promising performance.
no code implementations • 3 Feb 2024 • Zhuomin Chen, Jiaxing Zhang, Jingchao Ni, Xiaoting Li, Yuchen Bian, Md Mezbahul Islam, Ananda Mohan Mondal, Hua Wei, Dongsheng Luo
A popular paradigm for the explainability of GNNs is to identify explainable subgraphs by comparing their labels with the ones of original graphs.
no code implementations • 7 Feb 2024 • Xu Zheng, Farhad Shirani, Tianchun Wang, Shouwei Gao, Wenqian Dong, Wei Cheng, Dongsheng Luo
It is shown that the sample complexity of explanation-assisted learning can be arbitrarily smaller than explanation-agnostic learning.
no code implementations • 2 Mar 2024 • Jun-En Ding, Phan Nguyen Minh Thao, Wen-Chih Peng, Jian-Zhe Wang, Chun-Cheng Chug, Min-Chen Hsieh, Yun-Chien Tseng, Ling Chen, Dongsheng Luo, Chi-Te Wang, Pei-fu Chen, Feng Liu, Fang-Ming Hung
In our experiments, we observe that clinicalBERT and PubMed-BERT, when combined with attention fusion, can achieve an accuracy of 73% in multiclass chronic diseases and diabetes prediction.
no code implementations • 9 Mar 2024 • Tiejin Chen, Wenwang Huang, Linsey Pang, Dongsheng Luo, Hua Wei
This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated.