Graph Archives - ResearchW

Rong Yin – Graph Neural network

Dr. Rong yin distinguished academic and researcher in the field Graph Neural Network. She is a highly accomplished researcher with a focus on cutting-edge areas in artificial intelligence and machine learning. Over the past five years, she has made significant contributions, publishing over ten top conference and journal papers in esteemed venues such as NeurIPS, ICML, AAAI, IJCAI, IEEE TKDE, IEEE TNNL, PR, and IEEE TC. Recognized for her expertise, she has been invited to serve as a program committee member and reviewer for prestigious conferences and journals, including ICML, NeurIPS, ICLR, AAAI, and JMLR. One of her notable contributions includes proposing an efficient unsupervised learning algorithm based on the unified randomized sketches framework, paving the way for the application of machine learning in international important fields with massive data scenarios.

Additionally, she has designed a series of approximation algorithms for large-scale tasks such as regression, classification, ranking, and distributed learning. Her theoretical analyses have yielded optimal convergence rates for large-scale unsupervised learning, regression, and distributed learning, making significant strides in machine learning theory. As the principal or core backbone of more than 20 national or provincial key projects, including the Youth/General Fund of the National Natural Science Foundation of China and the National Key R&D Program, she has demonstrated leadership in advancing research in the field.

Professional Profiles:

Education

She earned her Ph.D. in Computer Science from the Institute of Information Engineering at the Chinese Academy of Sciences in July 2020, under the guidance of Prof. Dan Meng. Her research during this period has significantly contributed to the field, as evidenced by her subsequent achievements. Prior to her doctoral studies, she completed her M.S. in Computer Science at Harbin Institute of Technology in China in July 2016, with Prof. Xiaohong Su as her advisor. Her academic journey commenced with a B.S. in Thermal Energy and Power Engineering from Shenyang Aerospace University, China, in July 2014, under the mentorship of Prof. Rangshu Xu. Throughout her educational trajectory, she has demonstrated a commitment to academic excellence and has seamlessly transitioned from her undergraduate studies to achieving a Ph.D. in Computer Science, showcasing a continuous pursuit of knowledge and expertise in her chosen field.

Experience

She has been an integral part of the Institute of Information Engineering at the Chinese Academy of Sciences in China, serving as an Associate Researcher since December 2023. Her journey with the institute commenced in August 2020 when she was designated as an Associate Researcher to be Appointed, a position she transitioned into officially in December 2023 and continues to hold to the present. In her capacity as an Associate Researcher, she plays a crucial role in the ongoing research activities of the institute, contributing her expertise and insights to further the objectives of the organization. Her commitment to the field and the institute is evident in her sustained role, where she actively contributes to the research endeavors of the Institute of Information Engineering.

Academic achievements

Rong Yin, Yong Liu, Weiping Wang, Dan Meng. Scalable Kernel k-Means with Randomized Sketching: From Theory to Algorithm. In IEEE Transactions on Knowledge and Data Engineering, 2023, 35(9): 9210 – 9224. (TKDE 2023) (CCF-A, SCI-1, IF: 9.235). [PDF]
Rong Yin, Yong Liu, Weiping Wang, Dan Meng. Randomized Sketches for Clustering: Fast and Optimal Kernel k-Means. In Proceedings of Advances in Neural Information Processing Systems, 2022, 35: 6424-6436. (NeurIPS 2022) (CCF-A). [PDF]
Rong Yin, Yong Liu, Weiping Wang, Dan Meng. Distributed Nystrom Kernel Learning with Communications. In Proceedings of the 28th International Conference on Machine Learning, PMLR, 2021: 12019-12028. (ICML 2021) (CCF-A). [PDF]
Rong Yin, Yong Liu, Dan Meng. Distributed Randomized Sketching Kernel Learning. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022, 36(8): 8883-8891. (AAAI 2022) (CCF-A). [PDF]
Ruyue Liu, Rong Yin*, Yong Liu, Weiping Wang. ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network. In Proceedings of the 38th AAAI Conference on Artificial Intelligence, 2024. (AAAI 2024) (CCF-A, Corresponding author).
Rong Yin, Yong Liu, Lijing Lu, Weiping Wang, Dan Meng. Divide-and-Conquer Learning with Nyström: Optimal Rate and Algorithm. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020, 34(04): 6696-6703. (AAAI 2020) (CCF-A). [PDF]
Xueyan Wang, Jianlei Yang, Yinglin Zhao, Xiaotao Jia, Rong Yin, Xuhang Chen, Gang Qu, Weisheng Zhao. Triangle counting accelerations: From algorithm to in-memory computing architecture. IEEE Transactions on Computers, 2021, 71(10): 2462-2472. (TC 2021) (CCF-A, SCI-1, IF: 3.7). [PDF]
Rong Yin, Yong Liu, Weiping Wang, Dan Meng. Sketch Kernel Ridge Regression using Circulant Matrix: Algorithm and Theory. In IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(9): 3512-3524. (TNNLS 2020) (SCI-1, IF: 11.683). [PDF]
Ruyue Liu, Rong Yin*, Yong Liu, Weiping Wang. Unbiased and Augmentation-Free Self-Supervised Graph Representation Learning. In Pattern Recognition, 2024. (PR 2024) (SCI-1, IF: 8, Corresponding author). [PDF]
Rong Yin, Yong Liu, Weiping Wang, Dan Meng. Extremely sparse Johnson-Lindenstrauss transform: From theory to algorithm. In Proceedings of IEEE International Conference on Data Mining, 2020: 1376-1381. (ICDM 2020) (CCF-B). [PDF]
Lijing Lu, Rong Yin, Yong Liu, Weiping Wang. Hashing Based Prediction for Large-Scale Kernel Machine. In Proceedings of the International Conference on Computational Science, 2020: 496-509. (ICCS 2020). [PDF]
Jian Li, Yong Liu, Rong Yin, Weiping Wang. Multi-Class Learning using Unlabeled Samples: Theory and Algorithm. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019: 2880-2886. (IJCAI 2019) (CCF-A). [PDF]
Jian Li, Yong Liu, Rong Yin, Weiping Wang. Approximate Manifold Regularization: Scalable Algorithm and Generalization Analysis. In Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019: 2887-2893. (IJCAI 2019) (CCF-A). [PDF]

Publication

Multi-class learning: From theory to algorithm
Multi-Class Learning using Unlabeled Samples: Theory and Algorithm.
J Li, Y Liu, R Yin, W Wang

IJCAI, 2880-2886
Sketch kernel ridge regression using circulant matrix: Algorithm and theory
R Yin, Y Liu, W Wang, D Meng

IEEE transactions on neural networks and learning systems 31 (9), 3512-3524
Divide-and-conquer learning with nyström: Optimal rate and algorithm
R Yin, Y Liu, L Lu, W Wang, D Meng

Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 6696-6703
Triangle counting accelerations: From algorithm to in-memory computing architecture
X Wang, J Yang, Y Zhao, X Jia, R Yin, X Chen, G Qu, W Zhao

IEEE Transactions on Computers 71 (10), 2462-2472
Approximate Manifold Regularization: Scalable Algorithm and Generalization Analysis.
J Li, Y Liu, R Yin, W Wang

IJCAI, 2887-2893
Distributed Nystrom Kernel Learning with Communications
Rong Yin, Yong Liu, Weiping Wang, Dan Meng

Proceedings of the 28th International Conference on Machine Learning (ICML)
Extremely sparse Johnson-Lindenstrauss transform: From theory to algorithm
R Yin, Y Liu, W Wang, D Meng

2020 IEEE International Conference on Data Mining (ICDM), 1376-1381
Scalable Kernel -Means with Randomized Sketching: From Theory to Algorithm
Rong Yin, Yong Liu, Weiping Wang, Dan Meng

IEEE Transactions on Knowledge and Data Engineering (TKDE)

Introduction of Strategic Implementation Award in Network Science and Graph Analytics

Welcome to the Strategic Implementation Award in Network Science and Graph Analytics—an accolade designed to recognize and honor outstanding contributions in strategically implementing innovative solutions within the dynamic realms of network science and graph analytics.

Award Eligibility:

This award is open to individuals and teams engaged in network science and graph analytics, irrespective of age or organizational affiliation. Eligible candidates include researchers, industry professionals, and academics who have demonstrated excellence in the strategic implementation of solutions in this field.

Qualification and Publications:

Candidates should possess a background in network science or graph analytics and showcase a track record of significant contributions. Qualifications may include relevant academic degrees, industry experience, and a history of impactful publications in recognized journals or conferences.

Evaluation Criteria:

Entries will be evaluated based on the strategic significance of the implemented solutions, their impact on the field, and the innovative approaches employed. The judging panel will consider factors such as scalability, efficiency, and practical applications.

Submission Guidelines:

Submit a comprehensive biography, an abstract detailing the strategic implementation, and supporting files illustrating the impact of the work. Ensure that all submissions adhere to the specified format and are submitted by the stated deadline.

Recognition:

Recipients of the Strategic Implementation Award will receive a distinguished recognition, a certificate of achievement, and opportunities for collaboration and networking within the network science and graph analytics communities.

Community Impact:

The awarded projects will be showcased to inspire and inform the community, fostering knowledge exchange and collaboration for the advancement of network science and graph analytics.

Biography:

Provide a brief biography highlighting key achievements, contributions, and the impact of the strategic implementations in network science and graph analytics.

Abstract and Supporting Files:

Include a detailed abstract of the implemented solution and supporting files that provide evidence of its strategic impact. This may include case studies, data analyses, or other relevant documentation.

Rong Yin – Graph Neural network – Best Researcher Award

Rong Yin – Graph Neural network

Strategic Implementation Award in Network Science and Graph Analytics

Introduction of Strategic Implementation Award in Network Science and Graph Analytics

Award Eligibility:

Qualification and Publications:

Evaluation Criteria:

Submission Guidelines:

Recognition:

Community Impact:

Biography:

Abstract and Supporting Files:

RECOMMENDED

Mail us

Contact