Wenwen Gong

Wenwen Gong

Auto-generated profile, based on publicly available information

Wenwen Gong

Department of Computer Science and Technology, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 April 2020 in Information Sciences
Verified
Journal Article
Closed access
Lianyong QiLianyong Qi
Lianyong Qi
XZXuyun Zhang
Xuyun Zhang
SLShan Li
Shan Li
Shaohua WanShaohua Wan
Shaohua Wan
YWYiping Wen
Yiping Wen
WGWenwen Gong
Wenwen Gong

3 September 2021 in World Wide Web
Verified
Journal Article
Closed access
PDF file
LKLingzhen Kong
Lingzhen Kong
LWLina Wang
Lina Wang
WGWenwen Gong
Wenwen Gong
CYChao Yan
Chao Yan
Yucong DuanYucong Duan
Yucong Duan
Lianyong QiLianyong Qi
Lianyong Qi

13 May 2024
Verified
Conference Paper
Open access
DZDan Zhang
Dan Zhang
YGYangli-ao Geng
Yangli-ao Geng
WGWenwen Gong
Wenwen Gong
ZQZhongang Qi
Zhongang Qi
ZCZhiyu Chen
Zhiyu Chen
JTJie Tang
Jie Tang
Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by contrasting the embeddings between raw and augmented data. However, existing CL-based methods mostly focus on contrasting in a batch-wise way, failing to exploit potential regularity in the feature dimension. This leads to redundant solutions during the representation learning of users and items. In this work, we investigate how to employ both batch-wise CL (BCL) and feature-wise CL (FCL) for recommendation. We theoretically analyze the relation between BCL and FCL, and find that combining BCL and FCL helps eliminate redundant solutions but never misses an optimal solution. We propose a dual contrastive learning recommendation framework---RecDCL. In RecDCL, the FCL objective is designed to eliminate redundant solutions on user-item positive pairs and to optimize the uniform distributions within users and items using a polynomial kernel for driving the representations to be orthogonal; The BCL objective is utilized to generate contrastive embeddings on output vectors for enhancing the robustness of the representations. Extensive experiments on four widely-used benchmarks and one industry dataset demonstrate that RecDCL can consistently outperform the state-of-the-art GNNs-based and SSL-based models (with an improvement of up to 5.65% in terms of Recall@20). The source code is publicly available https://github.com/THUDM/RecDCL

1 March 2021 in Applied Soft Computing
Verified
Journal Article
Closed access
HKHuaizhen Kou
Huaizhen Kou
HLHanwen Liu
Hanwen Liu
Yucong DuanYucong Duan
Yucong Duan
WGWenwen Gong
Wenwen Gong
YXYanwei Xu
Yanwei Xu
Lianyong QiLianyong Qi
Lianyong Qi

27 September 2020 in Software: Practice and Experience
Verified
Journal Article
Closed access
PDF file
WGWenwen Gong
Wenwen Gong
CLChao Lv
Chao Lv
YDYucong Duan
Yucong Duan
ZLZengguang Liu
Zengguang Liu
MKMohammad R. Khosravi
Mohammad R. Khosravi
WDWanchun Dou
Wanchun Dou

13 January 2021 in Agriculture
Verified
Journal Article
Open access
PDF file
YWYawei Wang
Yawei Wang
YCYifei Chen
Yifei Chen
XZXiangnan Zhang
Xiangnan Zhang
WGWenwen Gong
Wenwen Gong
Leaf is an important organ for photosynthesis and transpiration associated with the plants’ growth. Through the study of leaf phenotype, it the physiological characteristics produced by the interaction of the morphological parameters with the environment can be understood. In order to realize the assessment of the spatial morphology of leaves, a method based on three-dimensional stereo vision was introduced to extract the shape information, including the length and width of the leaves. Firstly, a depth sensor was used to collect the point cloud of plant leaves. Then, the leaf coordinate system was adjusted by principal component analysis to extract the region of interest; and compared with a cross-sectional method, the geodesic distance method, we proposed a method based on the cutting plane to obtain the intersecting line of the three-dimensional leaf model. Eggplant leaves were used to compare the accuracy of these methods in the measurement of a single leaf.