Hui Guan

Orcid: 0000-0001-9128-2231

Affiliations:
  • University of Massachusetts Amherst, USA
  • North Carolina State University, Raleigh, USA (former)


According to our database1, Hui Guan authored at least 60 papers between 2016 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
A Tree-Structured Multitask Model Architectures Recommendation System.
IEEE Trans. Neural Networks Learn. Syst., November, 2024

DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling.
CoRR, 2024

Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models.
CoRR, 2024

Integrating Graph Neural Networks and Many-Body Expansion Theory for Potential Energy Surfaces.
CoRR, 2024

Understanding and Alleviating Memory Consumption in RLHF for LLMs.
CoRR, 2024

In-Situ Fine-Tuning of Wildlife Models in IoT-Enabled Camera Traps for Efficient Adaptation.
CoRR, 2024

ProTrain: Efficient LLM Training via Memory-Aware Techniques.
CoRR, 2024

Graph Neural Network Training Systems: A Performance Comparison of Full-Graph and Mini-Batch.
CoRR, 2024

Thinking Forward: Memory-Efficient Federated Finetuning of Language Models.
CoRR, 2024

Robust Image Watermarking using Stable Diffusion.
CoRR, 2024

Information-Enhanced Graph Neural Network for Transcending Homophily Barriers.
IEEE Access, 2024

CACTUS: Dynamically Switchable Context-aware micro-Classifiers for Efficient IoT Inference.
Proceedings of the 22nd Annual International Conference on Mobile Systems, 2024

AdapMTL: Adaptive Pruning Framework for Multitask Learning Model.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

Structured Pruning for Multi-Task Deep Neural Networks.
Proceedings of the 7th IEEE International Conference on Multimedia Information Processing and Retrieval, 2024

Loki: A System for Serving ML Inference Pipelines with Hardware and Accuracy Scaling.
Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing, 2024

GMorph: Accelerating Multi-DNN Inference via Model Fusion.
Proceedings of the Nineteenth European Conference on Computer Systems, 2024

Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling.
Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2024

2023
Efficient IoT Inference via Context-Awareness.
CoRR, 2023

Dynamic Gradient Balancing for Enhanced Adversarial Attacks on Multi-Task Models.
CoRR, 2023

GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism.
CoRR, 2023

An Alternative Hard-Parameter Sharing Paradigm for Multi-Domain Learning.
IEEE Access, 2023

Flow: Per-instance Personalized Federated Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios.
Proceedings of the 29th Annual International Conference on Mobile Computing and Networking, 2023

NUMAlloc: A Faster NUMA Memory Allocator.
Proceedings of the 2023 ACM SIGPLAN International Symposium on Memory Management, 2023

Flash: Concept Drift Adaptation in Federated Learning.
Proceedings of the International Conference on Machine Learning, 2023

Automatically marginalized MCMC in probabilistic programming.
Proceedings of the International Conference on Machine Learning, 2023

GraphMini: Accelerating Graph Pattern Matching Using Auxiliary Graphs.
Proceedings of the 32nd International Conference on Parallel Architectures and Compilation Techniques, 2023

2022
Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing.
CoRR, 2022

Break the Wall Between Homophily and Heterophily for Graph Representation Learning.
CoRR, 2022

Improving Subgraph Representation Learning via Multi-View Augmentation.
CoRR, 2022

AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Rethinking Hard-Parameter Sharing in Multi-Domain Learning.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2022

Enabling Near Real-Time NLU-Driven Natural Language Programming through Dynamic Grammar Graph-Based Translation.
Proceedings of the IEEE/ACM International Symposium on Code Generation and Optimization, 2022

A Tree-Structured Multi-Task Model Recommender.
Proceedings of the International Conference on Automated Machine Learning, 2022

2021
An Automatic Synthesizer of Advising Tools for High Performance Computing.
IEEE Trans. Parallel Distributed Syst., 2021

COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression.
Proc. VLDB Endow., 2021

Reuse-centric k-means configuration.
Inf. Syst., 2021

Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression.
CoRR, 2021

AutoMTL: A Programming Framework for Automated Multi-Task Learning.
CoRR, 2021

Rethinking Hard-Parameter Sharing in Multi-Task Learning.
CoRR, 2021

Scalable Graph Neural Network Training: The Case for Sampling.
CoRR, 2021

NumaPerf: Predictive and Full NUMA Profiling.
CoRR, 2021

CoCoPIE: enabling real-time AI on off-the-shelf mobile devices via compression-compilation co-design.
Commun. ACM, 2021

FreeLunch: Compression-based GPU Memory Management for Convolutional Neural Networks.
Proceedings of the IEEE/ACM Workshop on Memory Centric High Performance Computing, 2021

NumaPerf: predictive NUMA profiling.
Proceedings of the ICS '21: 2021 International Conference on Supercomputing, 2021

Recurrent Neural Networks Meet Context-Free Grammar: Two Birds with One Stone.
Proceedings of the IEEE International Conference on Data Mining, 2021

Deep NLP-based co-evolvement for synthesizing code analysis from natural language.
Proceedings of the CC '21: 30th ACM SIGPLAN International Conference on Compiler Construction, 2021

2020
SID-NISM: A Self-supervised Low-light Image Enhancement Framework.
CoRR, 2020

HISyn: human learning-inspired natural language programming.
Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

FLEET: Flexible Efficient Ensemble Training for Heterogeneous Deep Neural Networks.
Proceedings of the Third Conference on Machine Learning and Systems, 2020

2019
Post-Training 4-bit Quantization on Embedding Tables.
CoRR, 2019

Wootz: a compiler-based framework for fast CNN pruning via composability.
Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, 2019

In-Place Zero-Space Memory Protection for CNN.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Adaptive Deep Reuse: Accelerating CNN Training on the Fly.
Proceedings of the 35th IEEE International Conference on Data Engineering, 2019

2018
Exploring flexible communications for streamlining DNN ensemble training pipelines.
Proceedings of the International Conference for High Performance Computing, 2018

Reuse-Centric K-Means Configuration.
Proceedings of the 34th IEEE International Conference on Data Engineering, 2018

2017
First Study on Data Readiness Level.
CoRR, 2017

Egeria: a framework for automatic synthesis of HPC advising tools through multi-layered natural language processing.
Proceedings of the International Conference for High Performance Computing, 2017

Generalizations of the theory and deployment of triangular inequality for compiler-based strength reduction.
Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation, 2017

2016
A topological collapse for document summarization.
Proceedings of the 17th IEEE International Workshop on Signal Processing Advances in Wireless Communications, 2016


  Loading...