Qiyao Peng

Qiyao Peng

Auto-generated profile, based on publicly available information

Qiyao Peng

Tianjin University, Tianjin, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 January 2025
Verified
Conference Paper
Open access
PDF file
QPQiyao Peng
Qiyao Peng
HLHongtao Liu
Hongtao Liu
HHHua Huang
Hua Huang
JYJian Yang
Jian Yang
QYQing Yang
Qing Yang
MSMinglai Shao
Minglai Shao
Qiyao Peng, Hongtao Liu, Hua Huang, Jian Yang, Qing Yang, Minglai Shao. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

18 August 2023 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
HXHongyan Xu
Hongyan Xu
QPQiyao Peng
Qiyao Peng
HLHongtao Liu
Hongtao Liu
YSYueheng Sun
Yueheng Sun
WWWenjun Wang
Wenjun Wang
Personalized news recommendation aims to help users find news content they prefer, which has attracted increasing attention recently. There are two core issues in news recommendation: learning news representation and matching candidate news with user interests. In this context, “candidate” indicates potential for interest. Due to the superior ability to understand natural language demonstrated by Pretrained Language Models (PLMs), recent works utilize PLMs (e.g., BERT) to strengthen news modeling, obtaining more accurate user interest matching and achieving notable improvement in news recommendation. However, the existing PLM-based methods are usually incapable of fully exploring the fine-grained (i.e., word-level) relatedness between user behaviors and candidate news due to the heavy computational cost brought by PLMs. In this article, we propose a group-based personalized news recommendation method with long- and short-term matching mechanisms between users and candidate news based on PLMs to learn fine-grained matching efficiently and effectively. In our approach, we design to group user historical clicked news into chunks with quite shorter news sequences according to their clicked timestamps, which could alleviate the computation issues of PLMs. PLMs are applied in each group jointly with the candidate news to capture their word-level interaction, and global group-level matching is learned across different groups. In addition, the group-based mechanism could be naturally adapted for long- and short-term user representation learning, in which we build users’ long preferences from the representations of all groups and treat the last group as short interests, respectively. Finally, we employ a gate network to dynamically unify the group-level, long- and short-term representations, yielding comprehensive user-news matching effectively. Extensive experiments are conducted on two real-world datasets. The results show that our proposed method achieves superior performance in news recommendations.

26 November 2024 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
QPQiyao Peng
Qiyao Peng
HXHongyan Xu
Hongyan Xu
YWYinghui Wang
Yinghui Wang
HLHongtao Liu
Hongtao Liu
CHCuiying Huo
Cuiying Huo
WWWenjun Wang
Wenjun Wang
Finding experts is essential in Community Question Answering (CQA) platforms as it enables the effective routing of questions to potential users who can provide relevant answers. The key is to personalized learning expert representations based on their historical answered questions, and accurately matching them with target questions. Recently, the applications of Pre-Trained Language Models (PLMs) have gained significant attraction due to their impressive capability to comprehend textual data, and are widespread used across various domains. There have been some preliminary works exploring the usability of PLMs in expert finding, such as pre-training expert or question representations. However, these models usually learn pure text representations of experts from histories, disregarding personalized and fine-grained expert modeling. For alleviating this, we present a personalized pre-training and fine-tuning paradigm, which could effectively learn expert interest and expertise simultaneously. Specifically, in our pre-training framework, we integrate historical answered questions of one expert with one target question, and regard it as a candidate-aware expert-level input unit. Then, we fuse expert IDs into the pre-training for guiding the model to model personalized expert representations, which can help capture the unique characteristics and expertise of each individual expert. Additionally, in our pre-training task, we design (1) a question-level masked language model task to learn the relatedness between histories, enabling the modeling of question-level expert interest; (2) a vote-oriented task to capture question-level expert expertise by predicting the vote score the expert would receive. Through our pre-training framework and tasks, our approach could holistically learn expert representations including interests and expertise. Our method has been extensively evaluated on six real-world CQA datasets, and the experimental results consistently demonstrate the superiority of our approach over competitive baseline methods.

24 May 2024 in Information Processing & Management
Verified
Journal Article
Closed access
YWYinghui Wang
Yinghui Wang
QPQiyao Peng
Qiyao Peng
HLHongtao Liu
Hongtao Liu
HXHongyan Xu
Hongyan Xu
MSMinglai Shao
Minglai Shao
WWWenjun Wang
Wenjun Wang

30 May 2024 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
QPQiyao Peng
Qiyao Peng
YWYinghui Wang
Yinghui Wang
PJPengfei Jiao
Pengfei Jiao
Huaming WuHuaming Wu
Huaming Wu
WWWenjun Wang
Wenjun Wang
Network alignment, which integrates multiple network resources by identifying anchor nodes that exist in different networks, is beneficial for conducting comprehensive network analysis. Although there have been many studies on network alignment, most of them are limited to static scenarios and only can achieve acceptable top-$\alpha$ ($\alpha > 10$) results. In the absence of considering dynamic changes in networks, accurate network alignment (i.e., top-1 result) faces two problems: 1) Missing information: focusing solely on aligning networks at a specific time leads to low top-1 performance due to the lack of information from other time periods; 2) Confusing information: ignoring temporal information and focusing on aligning networks across the entire time span leads to low top-1 performance due to inability to distinguish the neighborhood nodes of anchor nodes. In this paper, we propose a dynamic network alignment method, which aims to achieve better top-1 alignment results with consider changing network structures over time. Towards this end, we learn the representations of nodes in the changing network structure with time, and preserve the consistency of anchor node pairs during the time-evolution process. First, we employ a Structure-Time-aware module to capture network dynamics while preserving network structure and learning node representations that incorporate temporal information. Second, we ensure the global and local consistency of anchor node pairs over time by utilizing linear and similarity functions, respectively. Finally, we determine whether two nodes are anchor node pairs by maintaining consistency between global, local, and node representations. Experimental results obtained from real-world datasets demonstrate that the proposed model achieves performance comparable to several state-of-the-art methods.

1 January 2022
Verified
Conference Paper
Open access
PDF file
QPQiyao Peng
Qiyao Peng
HLHongtao Liu
Hongtao Liu
Qiyao Peng, Hongtao Liu. Findings of the Association for Computational Linguistics: EMNLP 2022. 2022.