61 citations · 83 across the 6 of their papers we have counts for
6 papers
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Ruizhong Qiu, Hanqing Zeng, Yinglong Xia +15
Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRA…
LLM-Rec: Personalized Recommendation via Prompting Large Language Models
Hanjia Lyu, Song Jiang, Hanqing Zeng +7
Text-based recommendation holds a wide range of practical applications due to its versatility, as textual descriptions can represent nearly any type of item. However, directly empl…
GraphAGILE: An FPGA-based Overlay Accelerator for Low-latency GNN Inference
Bingyi Zhang, Hanqing Zeng, Viktor Prasanna
This paper presents GraphAGILE, a domain-specific FPGA-based overlay accelerator for graph neural network (GNN) inference. GraphAGILE consists of (1) \emph{a novel unified architec…
Low-latency Mini-batch GNN Inference on CPU-FPGA Heterogeneous Platform
Bingyi Zhang, Hanqing Zeng, Viktor Prasanna
Mini-batch inference of Graph Neural Networks (GNNs) is a key problem in many real-world applications. Recently, a GNN design principle of model depth-receptive field decoupling ha…
Accelerating Large Scale Real-Time GNN Inference using Channel Pruning
Hongkuan Zhou, Ajitesh Srivastava, Hanqing Zeng +2
Graph Neural Networks (GNNs) are proven to be powerful models to generate node embedding for downstream applications. However, due to the high computation complexity of GNN inferen…
Accurate, Efficient and Scalable Training of Graph Neural Networks
Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava +2
Graph Neural Networks (GNNs) are powerful deep learning models to generate node embeddings on graphs. When applying deep GNNs on large graphs, it is still challenging to perform tr…