2 citations · 6 across the 12 of their papers we have counts for
7 papers · 1 filter
Fiber Bundle Networks: A Geometric Machine Learning Paradigm
Dong Liu
We propose Fiber Bundle Networks (FiberNet), a novel machine learning framework integrating differential geometry with machine learning. Unlike traditional deep neural networks rel…
Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
Like Jian, Dong Liu
Federated learning (FL) enables decentralized clients to train a model collaboratively without sharing local data. A key distinction between FL and centralized learning is that cli…
FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation
Dong Liu, Yanxuan Yu, Jiayi Zhang +3
Diffusion Transformers (DiT) are powerful generative models but remain computationally intensive due to their iterative structure and deep transformer stacks. To alleviate this ine…
LLMEasyQuant: Scalable Quantization for Parallel and Distributed LLM Inference
Dong Liu, Yanxuan Yu
As large language models (LLMs) grow in size and deployment scale, quantization has become an essential technique for reducing memory footprint and improving inference efficiency.…
MT2ST: Adaptive Multi-Task to Single-Task Learning
Dong Liu, Yanxuan Yu
Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in mu…
GraphSnapShot: Caching Local Structure for Fast Graph Learning
Dong Liu, Roger Waleffe, Meng Jiang +1
In our recent research, we have developed a framework called GraphSnapShot, which has been proven an useful tool for graph learning acceleration. GraphSnapShot is a framework for f…
Efficient Graph Optimization via Distance-Aware Graph Representation Learning
Dong Liu, Yanxuan Yu
We propose an efficient framework that integrates distance-aware multi-hop message passing with dynamic topology refinement. Unlike standard GNNs that rely on shallow, fixed-hop ag…