Chao Zhou

Mr. Chao Zhou

orcid

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
21 October 2023
Verified
Conference Paper
Open access
XWXi Wu
Xi Wu
LYLiangwei Yang
Liangwei Yang
JGJibing Gong
Jibing Gong
CZChao Zhou
Chao Zhou
TLTianyu Lin
Tianyu Lin
PYPhilip S. Yu
Philip S. Yu
Collaborative filtering (CF) is a widely employed technique that predicts user preferences based on past interactions. Negative sampling plays a vital role in training CF-based models with implicit feedback. In this paper, we propose a novel perspective based on the sampling area to revisit existing sampling methods. We point out that current sampling methods mainly focus on Point-wise or Line-wise sampling, lacking flexibility and leaving a significant portion of the hard sampling area un-explored. To address this limitation, we propose Dimension Independent Mixup for Hard Negative Sampling (DINS), which is the first Area-wise sampling method for training CF-based models. DINS comprises three modules: Hard Boundary Definition, Dimension Independent Mixup, and Multi-hop Pooling. Experiments with real-world datasets on both matrix factorization and graph-based models demonstrate that DINS outperforms other negative sampling methods, establishing its effectiveness and superiority. Our work contributes a new perspective, introduces Area-wise sampling, and presents DINS as a novel approach that achieves state-of-the-art performance for negative sampling. Our implementations are available in PyTorch.

15 May 2024 in Electronics
Verified
Journal Article
Open access
PDF file
JPJiquan Peng
Jiquan Peng
JGJibing Gong
Jibing Gong
CZChao Zhou
Chao Zhou
QZQian Zang
Qian Zang
XFxiaohan fang
xiaohan fang
JYJing Yu
Jing Yu
Traditional collaborative filtering (CF)-based recommendation systems are often challenged by data sparsity. The recent research has recognized the potential of integrating new information sources, such as knowledge graphs, to address this issue. However, a common drawback is the neglect of the interplay between user–item interaction data and knowledge graph information, resulting in insufficient model performance due to coarse-grained feature fusion. To bridge this gap, in this paper, we propose a novel graph neural network (GNN) model called KGCFRec, which leverages both Knowledge Graph and user–item Collaborative Filtering information for an enhanced Recommender system. KGCFRec employs a dual-channel information propagation and aggregation mechanism to generate distinct representations for the collaborative knowledge graph and the user–item interaction graph. This is followed by an attention mechanism that adaptively fuses the knowledge graph with collaborative information, thereby refining the representations and narrowing the gap between them. The experiments conducted on three real-world datasets demonstrate that KGCFRec outperforms state-of-the-art methods. These promising results underscore the capability of KGCFRec to enhance recommendation accuracy by integrating knowledge graph information.

29 December 2022
Verified
Preprint
Open access
PDF file
CZChao Zhou
Chao Zhou
JGJibing Gong
Jibing Gong
QZQian Zang
Qian Zang
XFXiaohan Fang
Xiaohan Fang
KYKailun Yang
Kailun Yang
Traditional recommender systems that are based on CF (Collaborative Filtering) usually suffer from the user-item interaction data sparsity problem. With the development of end-to-end models founded on GNNs, the sparsity issue can be addressed by introducing additional sources of information such as knowledge information. However, these models are insufficient to fuse multi-source information. To fill this gap, in this paper, we propose an end-to-end GNN based model called KCIRec , which fuses both K _ nowledge graph C _ ollaborative information and user-item I _ nteraction information for Rec _ ommender system.Technically, a type of two-channels’ information propagation and aggregation mechanism are conceived to generate the representation of user-item interactions graph and collaborative knowledge graph respectively.In addition, we design an attention mechanism to adaptively fuse the collaborative information and knowledge graph information extracted from the above two graph. Extensive experiments on three real-world datasets show improvements of our proposed KCIRec model over thestate-of-the-art methods such as KGNN-LS, KGAT, and CKE. The promising results show that the proposed KCIRec is able to effectively fuse knowledge graph information and improve recommender systems’ accuracy.


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.