Fan Yu

Orcid: 0009-0001-2189-351X

Affiliations:
  • MindSpore open source project, Shenzhen, China
  • Huawei Technologies Ltd., Hangzhou, China
  • University of Science and Technology of China, Hefei, China (PhD 2009)


According to our database1, Fan Yu authored at least 33 papers between 2020 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Lafa: Unlocking Superior Memory Efficiency via Adaptive Metadata Strategy for Scalable Large-Scale Dataset Loading.
IEEE Trans. Big Data, April, 2026

Joint Optimization of Storage and Loading for High-Performance 3D Point Cloud Data Processing.
CoRR, March, 2026

Fate: Fasss sEsdge Inference of Mixture-of-Experts Models via Cross-Layer Gate.
Proceedings of the ACM Web Conference 2026, 2026

2025
Accurate Expert Predictions in MoE Inference via Cross-Layer Gate.
CoRR, February, 2025

Breaking barriers in 3D point cloud data processing: A unified system for efficient storage and high-throughput loading.
Expert Syst. Appl., 2025

Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, 2025

SlotPi: Physics-informed Object-centric Reasoning Models.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, 2025

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline.
Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2025

2024
SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

2023
Eigenvalue-Corrected Natural Gradient Based on a New Approximation.
Asia Pac. J. Oper. Res., February, 2023

2022
Elastic Deep Learning in Multi-Tenant GPU Clusters.
IEEE Trans. Parallel Distributed Syst., 2022

TensorOpt: Exploring the Tradeoffs in Distributed DNN Training With Auto-Parallelism.
IEEE Trans. Parallel Distributed Syst., 2022

Few-Shot Learning of Accurate Folding Landscape for Protein Structure Prediction.
CoRR, 2022

PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction.
CoRR, 2022

Leveraging Multi-view Inter-passage Interactions for Neural Document Ranking.
Proceedings of the WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining, Virtual Event / Tempe, AZ, USA, February 21, 2022

HGL: Accelerating Heterogeneous GNN Training with Holistic Representation and Optimization.
Proceedings of the SC22: International Conference for High Performance Computing, 2022

Meta-Auto-Decoder for Solving Parametric Partial Differential Equations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Universal PINNs Method for Solving Partial Differential Equations with a Point Source.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

Triple-Fact Retriever: An explainable reasoning retrieval model for multi-hop QA problem.
Proceedings of the 38th IEEE International Conference on Data Engineering, 2022

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

2021
Meta-Auto-Decoder for Solving Parametric Partial Differential Equations.
CoRR, 2021

Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks.
CoRR, 2021

Towards More Effective and Economic Sparsely-Activated Model.
CoRR, 2021

Vertex-Centric Visual Programming for Graph Neural Networks.
Proceedings of the SIGMOD '21: International Conference on Management of Data, 2021

Answer Complex Questions: Path Ranker Is All You Need.
Proceedings of the SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021

EPP-MVSNet: Epipolar-assembling based Depth Prediction for Multi-view Stereo.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Seastar: vertex-centric programming for graph neural networks.
Proceedings of the EuroSys '21: Sixteenth European Conference on Computer Systems, 2021

DGCL: an efficient communication library for distributed GNN training.
Proceedings of the EuroSys '21: Sixteenth European Conference on Computer Systems, 2021

SKFAC: Training Neural Networks With Faster Kronecker-Factored Approximate Curvature.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

A Trace-restricted Kronecker-Factored Approximation to Natural Gradient.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

THOR, Trace-based Hardware-driven Layer-Oriented Natural Gradient Descent Computation.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy.
CoRR, 2020

You Ought to Look Around: Precise, Large Span Action Detection.
Proceedings of the 25th International Conference on Pattern Recognition, 2020


  Loading...