Fast Inference of Removal-Based Node Influence

1 code implementation • 13 Mar 2024 • Weikai Li, Zhiping Xiao, Xiao Luo, Yizhou Sun

We propose a new method of evaluating node influence, which measures the prediction change of a trained GNN model caused by removing a node.

Adversarial Attack counterfactual +1

TIDE: Test Time Few Shot Object Detection

1 code implementation • 30 Nov 2023 • Weikai Li, Hongfeng Wei, Yanlai Wu, Jie Yang, Yudi Ruan, Yuan Li, Ying Tang

Few-shot object detection (FSOD) aims to extract semantic knowledge from limited object instances of novel categories within a target domain.

Data Augmentation Few-Shot Object Detection +3

When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks

no code implementations • 15 Nov 2023 • Hao Peng, Xiaozhi Wang, Jianhui Chen, Weikai Li, Yunjia Qi, Zimu Wang, Zhili Wu, Kaisheng Zeng, Bin Xu, Lei Hou, Juanzi Li

In this paper, we find that ICL falls short of handling specification-heavy tasks, which are tasks with complicated and extensive task specifications, requiring several hours for ordinary humans to master, such as traditional information extraction tasks.

In-Context Learning

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

1 code implementation • 15 Jun 2023 • Jifan Yu, Xiaozhi Wang, Shangqing Tu, Shulin Cao, Daniel Zhang-li, Xin Lv, Hao Peng, Zijun Yao, Xiaohan Zhang, Hanming Li, Chunyang Li, Zheyuan Zhang, Yushi Bai, Yantao Liu, Amy Xin, Nianyi Lin, Kaifeng Yun, Linlu Gong, Jianhui Chen, Zhili Wu, Yunjia Qi, Weikai Li, Yong Guan, Kaisheng Zeng, Ji Qi, Hailong Jin, Jinxin Liu, Yu Gu, Yuan YAO, Ning Ding, Lei Hou, Zhiyuan Liu, Bin Xu, Jie Tang, Juanzi Li

The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.

Benchmarking Hallucination +1

Rethinking the Setting of Semi-supervised Learning on Graphs

1 code implementation • 28 May 2022 • Ziang Li, Ming Ding, Weikai Li, Zihan Wang, Ziyu Zeng, Yukuo Cen, Jie Tang

graph benchmark (IGB) consisting of 4 datasets.

Jacobian Norm for Unsupervised Source-Free Domain Adaptation

no code implementations • 7 Apr 2022 • Weikai Li, Meng Cao, Songcan Chen

Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge from a well-trained source model to a related but unlabeled target domain.

Source-Free Domain Adaptation

Partial Domain Adaptation without Domain Alignment

1 code implementation • 29 Aug 2021 • Weikai Li, Songcan Chen

Considering the difficulty of perfect alignment in solving PDA, we turn to focus on the model smoothness while discard the riskier domain alignment to enhance the adaptability of the model.

Partial Domain Adaptation Unsupervised Domain Adaptation

The Reconfiguration Pattern of Individual Brain Metabolic Connectome for Parkinson's Disease Identification

no code implementations • 29 Apr 2021 • Weikai Li, Yongxiang Tang, Zhengxia Wang, Shuo Hu, Xin Gao

We aim to establish an individual metabolic connectome method to characterize the aberrant connectivity patterns and topological alterations of the individual-level brain metabolic connectome and their diagnostic value in PD.

Leave Zero Out: Towards a No-Cross-Validation Approach for Model Selection

1 code implementation • 24 Dec 2020 • Weikai Li, Chuanxing Geng, Songcan Chen

On the one hand, for small data cases, CV suffers a conservatively biased estimation, since some part of the limited data has to hold out for validation.

Model Selection

Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces

1 code implementation • 1 Sep 2020 • Weikai Li, Songcan Chen

Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift.

Partial Domain Adaptation Transfer Learning +1