Fusheng Jin

Dr. Fusheng Jin

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 August 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YCYurong Cheng
Yurong Cheng
LCLei Chen
Lei Chen
YYYe Yuan
Ye Yuan
GWGuoren Wang
Guoren Wang
BLBoyang Li
Boyang Li
FJFusheng Jin
Fusheng Jin
Real-life graph datasets extracted from Web are inevitably full of incompleteness, conflicts, and redundancies, so graph data cleaning shows its necessity. Although rules like data dependencies have been widely studied in relational data repairing, very few works exist to repair the graph data. In this paper, we introduce a repairing semantic for graphs, called Graph-Repairing Rules (GRRs). This semantic can capture the incompleteness, conflicts, and redundancies in the graphs and indicate how to correct these errors. However, this graph repairing semantic can only repair the graphs strictly isomorphic to the rule patterns, which decreases the utility of rules. To overcome this shortcoming, we further propose a flexible rule-based graph repairing semantic. We study three fundamental problems associated with both GRRs and -GRRs, implication, consistency and termination, which show whether a given set of rules make sense. Repairing the graph data using GRRs or -GRRs involves a problem of finding isomorphic subgraphs of the graph data, which is NP-complete. To efficiently circumvent the complex calculation of subgraph isomorphism, we design a decomposition-and-join strategy to solve this problem. For -GRRs, we further develop an index-based method. Extensive experiments on real datasets show that our two graph repairing semantic and corresponding repairing algorithms can effectively and efficiently repair real-life graph data.

11 January 2023 in Future Generation Computer Systems
Verified
Journal Article
Open access
RYRunde Yu
Runde Yu
FJFusheng Jin
Fusheng Jin
ZQZhuang Qiao
Zhuang Qiao
YYYe Yuan
Ye Yuan
GWGuoren Wang
Guoren Wang

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
CQChangqing Qiu
Changqing Qiu
FJFusheng Jin
Fusheng Jin
YZYining Zhang
Yining Zhang
Recently, the explanation of neural network models has garnered considerable research attention. In computer vision, CAM (Class Activation Map)-based methods and LRP (Layer-wise Relevance Propagation) method are two common explanation methods. However, since most CAM-based methods can only generate global weights, they can only generate coarse-grained explanations at a deep layer. LRP and its variants, on the other hand, can generate fine-grained explanations. But the faithfulness of the explanations is too low. To address these challenges, in this paper, we propose FG-CAM (Fine-Grained CAM), which extends CAM-based methods to enable generating fine-grained and high-faithfulness explanations. FG-CAM uses the relationship between two adjacent layers of feature maps with resolution differences to gradually increase the explanation resolution, while finding the contributing pixels and filtering out the pixels that do not contribute. Our method not only solves the shortcoming of CAM-based methods without changing their characteristics, but also generates fine-grained explanations that have higher faithfulness than LRP and its variants. We also present FG-CAM with denoising, which is a variant of FG-CAM and is able to generate less noisy explanations with almost no change in explanation faithfulness. Experimental results show that the performance of FG-CAM is almost unaffected by the explanation resolution. FG-CAM outperforms existing CAM-based methods significantly in both shallow and intermediate layers, and outperforms LRP and its variants significantly in the input layer. Our code is available at https://github.com/dongmo-qcq/FG-CAM.

1 March 2021 in Neurocomputing
Verified
Journal Article
Closed access
XHXiangyu Han
Xiangyu Han
FJFusheng Jin
Fusheng Jin
RWRunan Wang
Runan Wang
Shuliang WangShuliang Wang
Shuliang Wang
YYYe Yuan
Ye Yuan

13 September 2021 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
CWChuanbing Wan
Chuanbing Wan
FJFusheng Jin
Fusheng Jin
ZQZhuang Qiao
Zhuang Qiao
WZWeiwei Zhang
Weiwei Zhang
YYYe Yuan
Ye Yuan

21 October 2024
Verified
Conference Paper
Open access
ZLZening Li
Zening Li
RLRonghua Li
Ronghua Li
MLMeihao Liao
Meihao Liao
FJFusheng Jin
Fusheng Jin
GWGuoren Wang
Guoren Wang