Xi Wu

Dr. Xi Wu

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 February 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
LWLulu Wang
Lulu Wang
KYKai Yu
Kai Yu
AWAishan Wumaier
Aishan Wumaier
PZPeng Zhang
Peng Zhang
TYTuergen Yibulayin
Tuergen Yibulayin
MMMaihemuti Maimaiti
Maihemuti Maimaiti
Extractive approaches have been the mainstream paradigm for identifying overlapping entity–relation extraction. However, limited by their inherently methodological flaws, which hardly deal with three issues: hierarchical dependent entity–relations, implicit entity–relations, and entity normalization. Recent advances have proposed an effective solution based on generative language models, which cast entity–relation extraction as a sequence-to-sequence text generation task. Inspired by the observation that humans learn by getting to the bottom of things, we propose a novel framework, namely GenRE, Generative multi-turn question answering with contrastive learning for entity–relation extraction. Specifically, a template-based question prompt generation first is designed to answer in different turns. We then formulate entity–relation extraction as a generative question answering task based on the general language model instead of span-based machine reading comprehension. Meanwhile, the contrastive learning strategy in fine-tuning is introduced to add negative samples to mitigate the exposure bias inherent in generative models. Our extensive experiments demonstrate that GenRE performs competitively on two public datasets and a custom dataset, highlighting its superiority in entity normalization and implicit entity–relation extraction. (The code is available at https://github.com/lovelyllwang/GenRE).

1 August 2025 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
XFxiaohan fang
xiaohan fang
QZQian Zang
Qian Zang
JGJibing Gong
Jibing Gong
TFTao Fang
Tao Fang
YXYili Xu
Yili Xu
XWXi Wu
Xi Wu

23 August 2025 in Multimedia Systems
Verified
Journal Article
Closed access
PDF file
YZYi Zhao
Yi Zhao
JZJin Zhang
Jin Zhang
JGJibing Gong
Jibing Gong
JPJiquan Peng
Jiquan Peng
XWXi Wu
Xi Wu
SDShuying Du
Shuying Du

20 October 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
SCShisen Cai
Shisen Cai
XWXi Wu
Xi Wu
MMMaihemuti Maimaiti
Maihemuti Maimaiti
YCYichang Chen
Yichang Chen
ZWZhixiang Wang
Zhixiang Wang
JZJiong Zheng
Jiong Zheng
Recently, the focus of entity linking research has centered on the zero-shot scenario, where the entity purposed to be labeled at the time of testing was never observed during the training phase, or it may belong to a different domain than the source domain. Current studies have used BERT as the base encoder, as it effectively establishes distributional links between source and target domains. The currently available negative sampling methods all use an extractive approach, which makes it difficult for the models to learn diverse and more challenging negative samples. To address this problem, we propose a generative negative sampling method, adaptive_mixup_hard, which generates more difficult negative entities by fusing the features of both positive and negative samples on top of hard negative sampling and introduces a transformable adaptive parameter, W, to increase the diversity of negative samples. Next, we fuse our method with the Biencoder architecture and evaluate its performance under three different score functions. Ultimately, experimental results on the standard benchmark dataset, Zeshel, demonstrate the effectiveness of our method.

24 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
XWXi Wu
Xi Wu
DZDan Zhang
Dan Zhang
CZChao Zhou
Chao Zhou
LYLiangwei Yang
Liangwei Yang
TLTianyu Lin
Tianyu Lin
JGJibing Gong
Jibing Gong
Recommender systems (RecSys) have become essential in modern society, driving user engagement and satisfaction across diverse online platforms. Most RecSys focuses on designing a powerful encoder to embed users and items into high-dimensional vector representation space, with loss functions optimizing their representation distributions. Recent studies reveal that directly optimizing key properties of the representation distribution, such as alignment and uniformity, can outperform complex encoder designs. However, existing methods for optimizing critical attributes overlook the impact of dataset sparsity on the model: limited user-item interactions lead to sparse alignment, while excessive interactions result in uneven uniformity, both of which degrade performance. In this paper, we identify the sparse alignment and uneven uniformity issues, and further propose Regularized Alignment and Uniformity (RAU) to cope with these two issues accordingly. RAU consists of two novel regularization methods for alignment and uniformity to learn better user/item representation. 1) Center-strengthened alignment further aligns the average in-batch user/item representation to provide an enhanced alignment signal and further minimize the disparity between user and item representation. 2) Low-variance-guided uniformity minimizes the variance of pairwise distances along with uniformity, which provides extra guidance to a more stabilized uniformity increase during training. We conducted extensive experiments on three real-world datasets, and the proposed RAU resulted in significant performance improvements compared to current state-of-the-art CF methods, which confirms the advantages of the two proposed regularization methods.

26 September 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
SCShisen Cai
Shisen Cai
XWXi Wu
Xi Wu
MMMaihemuti Maimaiti
Maihemuti Maimaiti
YCYichang Chen
Yichang Chen
ZWZhixiang Wang
Zhixiang Wang
JZJiong Zheng
Jiong Zheng
Recently, the focus of entity linking research has centered on the zero-shot scenario, where the entity mention to be labeled at the time of testing was never observed during the training phase or may belong to a different domain than the source domain. Current studies have used BERT as the base encoder as it effectively establishes distributional links between source and target domains. The currently available negative sampling methods all use an extractive approach, which makes it difficult for the models to learn diverse and more challenging negative samples. To address this problem, we propose a generative negative sampling method, Adaptive_mixup_hard, which generates more difficult negative entities by fusing the features of both positive and negative samples on top of hard negative sampling and introduces a transformable adaptive parameter W to increase the diversity of negative samples. Next, we fuse our method with the Biencoder architecture and evaluate its performance under three different score functions. Ultimately, experimental results on the standard benchmark dataset Zeshel demonstrate the effectiveness of our method.