Reasoning Graph Enhanced Exemplars Retrieval for In-Context Learning

1 code implementation • 17 Sep 2024 • Yukang Lin, Bingchen Zhong, Shuoran Jiang, Joanna Siebert, Qingcai Chen

Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique.

Few-Shot Learning In-Context Learning +4

ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization

1 code implementation • 23 Dec 2023 • Shuoran Jiang, Qingcai Chen, Youchen Pan, Yang Xiang, Yukang Lin, XiangPing Wu, Chuanyi Liu, Xiaobao Song

Our convergence analysis and experiments prove this is a better way to improve convergence stability and rate in ZO-SGD.

Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning

no code implementations • 24 Oct 2023 • Shuoran Jiang, Qingcai Chen, Yang Xiang, Youcheng Pan, XiangPing Wu

However, existing ADA methods fail to account for the confounder properly, which is the root cause of the source data distribution that differs from the target domains.

Domain Adaptation Representation Learning

Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning

1 code implementation • ACL 2021 • Shuoran Jiang, Qingcai Chen, Xin Liu, Baotian Hu, Lisai Zhang

In this study, we define the spectral graph convolutional network with the high-order dynamic Chebyshev approximation (HDGCN), which augments the multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutional layer.

Text-Guided Neural Image Inpainting

1 code implementation • 7 Apr 2020 • Lisai Zhang, Qingcai Chen, Baotian Hu, Shuoran Jiang

To fulfill such a task, we propose a novel inpainting model named Text-Guided Dual Attention Inpainting Network (TDANet).

Descriptive Image Inpainting +4