Search Results for author: Jingyi Li

Found 9 papers, 1 papers with code

Pluto and Charon: A Time and Memory Efficient Collaborative Edge AI Framework for Personal LLMs Fine-Tuning

no code implementations20 Aug 2024 Bei Ouyang, Shengyuan Ye, Liekang Zeng, Tianyi Qian, Jingyi Li, Xu Chen

The use of the activation cache eliminates the need for forward pass through the LLM backbone, enabling exclusive fine-tuning of the Parallel Adapters using data parallelism.

parameter-efficient fine-tuning

Design and Optimization of Hierarchical Gradient Coding for Distributed Learning at Edge Devices

no code implementations16 Jun 2024 Weiheng Tang, Jingyi Li, Lin Chen, Xu Chen

In this paper, along a different line, we investigate the problem of mitigating the straggler effect in hierarchical distributed learning systems with an additional layer composed of edge nodes.

Edge-computing

IMFL-AIGC: Incentive Mechanism Design for Federated Learning Empowered by Artificial Intelligence Generated Content

no code implementations12 Jun 2024 Guangjing Huang, Qiong Wu, Jingyi Li, Xu Chen

Federated learning (FL) has emerged as a promising paradigm that enables clients to collaboratively train a shared global model without uploading their local data.

Federated Learning

Study of the Impact of the Big Data Era on Accounting and Auditing

no code implementations11 Mar 2024 Yuxiang Sun, Jingyi Li, Mengdie Lu, Zongying Guo

Keywords: Big Data, Accounting, Audit, Data Privacy, AI, Machine Learning, Transparency.

Anomaly Detection

Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks

no code implementations6 Sep 2023 Jingyi Li, Guocheng Liao, Lin Chen, Xu Chen

In this paper, we propose a framework of Roulette, which is a task-oriented semantic privacy-preserving collaborative inference framework for deep learning classifiers.

Collaborative Inference Privacy Preserving +1

Clustered Embedding Learning for Recommender Systems

no code implementations3 Feb 2023 Yizhou Chen, Guangda Huzhang, AnXiang Zeng, Qingtao Yu, Hui Sun, Heng-yi Li, Jingyi Li, Yabo Ni, Han Yu, Zhiming Zhou

However, such a method has two important limitations in real-world applications: 1) it is hard to learn embeddings that generalize well for users and items with rare interactions on their own; and 2) it may incur unbearably high memory costs when the number of users and items scales up.

Recommendation Systems

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

1 code implementation27 Oct 2022 Jingyi Li, Weiping tu, Li Xiao

Voice conversion (VC) can be achieved by first extracting source content information and target speaker information, and then reconstructing waveform with these information.

Data Augmentation text annotation +2

Fact-based Content Weighting for Evaluating Abstractive Summarisation

no code implementations ACL 2020 Xinnuo Xu, Ond{\v{r}}ej Du{\v{s}}ek, Jingyi Li, Verena Rieser, Ioannis Konstas

Abstractive summarisation is notoriously hard to evaluate since standard word-overlap-based metrics are insufficient.

Confiding in and Listening to Virtual Agents: The Effect of Personality

no code implementations2 Nov 2018 Jingyi Li, Michelle X. Zhou, Huahai Yang, Gloria Mark

We investigate how the personality of a virtual interviewer influences a user's behavior from two perspectives: the user's willingness to confide in, and listen to, a virtual interviewer.

Cannot find the paper you are looking for? You can Submit a new open access paper.