ORCID Profile
0000-0002-5056-0351
Current Organisations
Alibaba Group (China)
,
University of Vermont
,
Zhejiang University
,
South China University of Technology
,
TCL Research America
,
Hangzhou Yugu Technology Co.,Ltd
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Related Links
Publications
Toward Graph Self-Supervised Learning With Contrastive Adjusted Zooming
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Towards Efficient Motif-based Graph Partitioning: An Adaptive Sampling Approach
Publisher: IEEE
Date: 04-2021
Evaluation of apical clips placed during axillary dissection demonstrates potential under‐coverage of axillary radiation therapy target volumes during breast cancer regional nodal irradiation
Publisher: Wiley
Date: 25-11-2021
Abstract: Evidence‐based Australian guidelines (eviQ) recommend adjuvant supraclavicular fossa irradiation after axillary lymph node dissection (ALND) in node‐positive breast cancer patients. Disparity between surgically determined versus computed tomography (CT) determined nodal volumes may result in discontiguous nodal volumes and untreated nodal tissue. We examine the extent of untreated nodal tissue in women with breast cancer post‐level II or III ALND and adjuvant radiation therapy (RT) using ESTRO contouring guidelines. Female breast cancer patients who underwent level II and III ALND with apical clip placement from 2016 to 2020 and CT simulated in supine position were included. CT‐defined axillary level II‐IV volumes were contoured using ESTRO guidelines. The distance between the apical clip and RT nodal volumes was measured to indicate extent of untreated tissue. Of 34 eligible patients treated by 7 surgeons, 76% had level II ALND and 24% level III ALND. Only 5.9% of clips entirely encompassed the corresponding RT nodal volumes. 55.9% of clips fell within and 44.1% fell inferolaterally outside the corresponding RT nodal volumes. A median 3.6 cm (range 0–7.5 cm) of undissected nodal tissue would not be included within standard RT target volumes following eviQ recommendations. There is a disparity between surgically determined versus CT determined axillary nodal volumes, leading to discontiguous nodal volumes and untreated axillary nodal tissue, despite following standard radiation contouring guidelines. Intraoperatively placed apical axillary clips may assist radiation oncologists to accurately delineate undissected nodal tissues at risk.
Domain Adaptation for Anomaly Detection on Heterogeneous Graphs in E-Commerce
Publisher: Springer Nature Switzerland
Date: 2023
Incremental Maximal Clique Enumeration for Hybrid Edge Changes in Large Dynamic Graphs
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
HGNAS++: Efficient Architecture Search for Heterogeneous Graph Neural Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-0025
CMAL: Cost-Effective Multi-Label Active Learning by Querying Subexamples
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2022
eFraudCom: An E-commerce Fraud Detection System via Competitive Graph Neural Networks
Publisher: Association for Computing Machinery (ACM)
Date: 07-03-2022
DOI: 10.1145/3474379
Abstract: With the development of e-commerce, fraud behaviors have been becoming one of the biggest threats to the e-commerce business. Fraud behaviors seriously damage the ranking system of e-commerce platforms and adversely influence the shopping experience of users. It is of great practical value to detect fraud behaviors on e-commerce platforms. However, the task is non-trivial, since the adversarial action taken by fraudsters. Existing fraud detection systems used in the e-commerce industry easily suffer from performance decay and can not adapt to the upgrade of fraud patterns, as they take already known fraud behaviors as supervision information to detect other suspicious behaviors. In this article, we propose a competitive graph neural networks (CGNN)-based fraud detection system (eFraudCom) to detect fraud behaviors at one of the largest e-commerce platforms, “Taobao” 1 . In the eFraudCom system, (1) the competitive graph neural networks (CGNN) as the core part of eFraudCom can classify behaviors of users directly by modeling the distributions of normal and fraud behaviors separately (2) some normal behaviors will be utilized as weak supervision information to guide the CGNN to build the profile for normal behaviors that are more stable than fraud behaviors. The algorithm dependency on fraud behaviors will be eliminated, which enables eFraudCom to detect fraud behaviors in presence of the new fraud patterns (3) the mutual information regularization term can maximize the separability between normal and fraud behaviors to further improve CGNN. eFraudCom is implemented into a prototype system and the performance of the system is evaluated by extensive experiments. The experiments on two Taobao and two public datasets demonstrate that the proposed deep framework CGNN is superior to other baselines in detecting fraud behaviors. A case study on Taobao datasets verifies that CGNN is still robust when the fraud patterns have been upgraded.
CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing
Publisher: ACM
Date: 30-04-2023
Online Active Learning for Drifting Data Streams
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
eRiskCom: an e-commerce risky community detection platform
Publisher: Springer Science and Business Media LLC
Date: 17-01-2022
Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Group-based Fraud Detection Network on e-Commerce Platforms
Publisher: ACM
Date: 04-08-2023
TigeCMN: On exploration of temporal interaction graph embedding via Coupled Memory Neural Networks
Publisher: Elsevier BV
Date: 08-2021
Disentangled Deep Multivariate Hawkes Process for Learning Event Sequences
Publisher: IEEE
Date: 12-2021
Related Organisations
Related Funding Activities
No related grants have been discovered for Zhao Li.