no code implementations • 3 Apr 2024 • Jingyang Zhang, Jingwei Sun, Eric Yeats, Yang Ouyang, Martin Kuo, Jianyi Zhang, Hao Yang, Hai Li
The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and test data contamination.
1 code implementation • 3 Dec 2023 • Yuqi Jia, Saeed Vahidian, Jingwei Sun, Jianyi Zhang, Vyacheslav Kungurtsev, Neil Zhenqiang Gong, Yiran Chen
This process allows local devices to train smaller surrogate models while enabling the training of a larger global model on the server, effectively minimizing resource utilization.
no code implementations • 8 Nov 2023 • Martin Kuo, Jianyi Zhang, Yiran Chen
Building on the cost-efficient pretraining advancements brought about by Crammed BERT, we enhance its performance and interpretability further by introducing a novel pretrained model Dependency Agreement Crammed BERT (DACBERT) and its two-stage pretraining framework - Dependency Agreement Pretraining.
1 code implementation • 9 May 2023 • Jianyi Zhang, Saeed Vahidian, Martin Kuo, Chunyuan Li, Ruiyi Zhang, Tong Yu, Yufan Zhou, Guoyin Wang, Yiran Chen
This repository offers a foundational framework for exploring federated fine-tuning of LLMs using heterogeneous instructions across diverse categories.
no code implementations • 7 Oct 2022 • Zhixu Du, Jingwei Sun, Ang Li, Pin-Yu Chen, Jianyi Zhang, Hai "Helen" Li, Yiran Chen
We also show that layer normalization is a better choice in FL which can mitigate the external covariate shift and improve the performance of the global model.
no code implementations • 6 Oct 2022 • Jianyi Zhang, Yiran Chen, Jianshu Chen
Developing neural architectures that are capable of logical reasoning has become increasingly important for a wide range of applications (e. g., natural language processing).
no code implementations • 30 Sep 2022 • Jianyi Zhang, Ang Li, Minxue Tang, Jingwei Sun, Xiang Chen, Fan Zhang, Changyou Chen, Yiran Chen, Hai Li
Based on this measure, we also design a computation-efficient client sampling strategy, such that the actively selected clients will generate a more class-balanced grouped dataset with theoretical guarantees.
no code implementations • 8 Sep 2022 • Minxue Tang, Jianyi Zhang, Mingyuan Ma, Louis DiValentin, Aolin Ding, Amin Hassanzadeh, Hai Li, Yiran Chen
However, the high demand for memory capacity and computing power makes large-scale federated adversarial training infeasible on resource-constrained edge devices.
no code implementations • 30 May 2022 • Jianyi Zhang, Xuanxi Huang, Yaqi Liu, Yuyang Han, Zixiao Xiang
Our method can classify whether a CT image has been tampered and locate the tampered position.
no code implementations • 27 Apr 2021 • Weituo Hao, Mostafa El-Khamy, Jungwon Lee, Jianyi Zhang, Kevin J Liang, Changyou Chen, Lawrence Carin
Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data.
no code implementations • 26 Feb 2021 • Jianyi Zhang, Paul Weng
Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance.
no code implementations • 23 Feb 2021 • Matthieu Zimmer, Xuening Feng, Claire Glanois, Zhaohui Jiang, Jianyi Zhang, Paul Weng, Dong Li, Jianye Hao, Wulong Liu
As a step in this direction, we propose a novel neural-logic architecture, called differentiable logic machine (DLM), that can solve both inductive logic programming (ILP) and reinforcement learning (RL) problems, where the solution can be interpreted as a first-order logic program.
no code implementations • 10 Feb 2021 • Qian Yang, Jianyi Zhang, Weituo Hao, Gregory Spell, Lawrence Carin
While different data-driven deep learning models have been developed to mitigate the diagnosis of COVID-19, the data itself is still scarce due to patient privacy concerns.
4 code implementations • ICLR 2020 • Ruqi Zhang, Chunyuan Li, Jianyi Zhang, Changyou Chen, Andrew Gordon Wilson
The posteriors over neural network weights are high dimensional and multimodal.
no code implementations • 21 Nov 2018 • Yang Zhao, Jianyi Zhang, Changyou Chen
Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models.
no code implementations • ICML 2020 • Jianyi Zhang, Yang Zhao, Changyou Chen
Stochastic particle-optimization sampling (SPOS) is a recently-developed scalable Bayesian sampling framework that unifies stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) algorithms based on Wasserstein gradient flows.
no code implementations • 27 Sep 2018 • Jianyi Zhang, Ruiyi Zhang, Changyou Chen
With such theoretical guarantees, SPOS can be safely and effectively applied on both Bayesian DL and deep RL tasks.
no code implementations • 5 Sep 2018 • Jianyi Zhang, Ruiyi Zhang, Lawrence Carin, Changyou Chen
Particle-optimization-based sampling (POS) is a recently developed effective sampling technique that interactively updates a set of particles.