Ruiguo Yu

Ruiguo Yu

Auto-generated profile, based on publicly available information

Ruiguo Yu

College of Intelligence and Computing, Tianjin University, Tianjin 300350, P. R. China

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
27 February 2023
Verified
Conference Paper
Open access
XLXuewei Li
Xuewei Li
ASAitong Sun
Aitong Sun
MZMankun Zhao
Mankun Zhao
JYJian Yu
Jian Yu
KZKun Zhu
Kun Zhu
RYRuiguo Yu
Ruiguo Yu
Sequential recommendation aims to capture users' dynamic preferences, in which data sparsity is a key problem. Most contrastive learning models leverage data augmentation to address this problem, but they amplify noises in original sequences. Contrastive learning has the assumption that two views (positive pairs) obtained from the same user behavior sequence must be similar. However, noises typically disturb the user's main intention, which results in the dissimilarity of two views. To address this problem, in this work, we formalize the denoising problem by selecting the user's main intention, and apply contrastive learning for the first time under this topic, i.e., we propose a novel framework, namely Multi-Intention Oriented Contrastive Learning Recommender (IOCRec). In order to create high-quality views with intent-level, we fuse local and global intentions to unify sequential patterns and intent-level self-supervision signals. Specifically, we design the sequence encoder in IOCRec which includes three modules: local module, global module and disentangled module. The global module can capture users' global preferences, which is independent of the local module. The disentangled module can obtain multi-intention behind global and local representations. From a fine-grained perspective, IOCRec separates different intentions to guide the denoising process. Extensive experiments on four widely-used real datasets demonstrate the effectiveness of our new method for sequential recommendation.

25 December 2018 in International Journal of Distributed Sensor Networks
Verified
Journal Article
Open access
MYMei Yu
Mei Yu
JZJie Zhang
Jie Zhang
JWJianrong Wang
Jianrong Wang
JGJie Gao
Jie Gao
TXTianyi Xu
Tianyi Xu
RYRuiguo Yu
Ruiguo Yu
Now, the security and privacy-preserving of Internet of Things are receiving more attention. This article proposes a new method of Internet of Things security and privacy preserving by combining differentiated nodes, precision clustering, RSA, multi-signature, and blockchain. To calculate the node rank value in Internet of Things, the number of nodes’ links is taken as the weight of nodes based on PageRank. This method increases the node rank values’ difference between nodes. Accurate clustering determines the initial central nodes of k-means based on the differentiated node rank values, which effectively differentiates the active and inactive nodes in Internet of Things and achieve different levels of protection. To ensure data’s reusability, we adopt the multi-signature. And considering node’s incoming nodes have certain decision on whether data can be transmitted, we filter out two nodes with the highest node rank value from active node’s incoming nodes to do 2/3 multi-signature which saves resources. We encrypt and sign the transmitted data with RSA, helping receivers to verify data. Data are transmitted safely through the blockchain. Successful validation indicates successful transmission. Experiments show that the proposed method can effectively distinguish between active and inactive nodes, which increases the difficulty of attackers’ attack and effectively protects the security and privacy of Internet of Things nodes and data.

4 August 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
RZRuixuan Zhang
Ruixuan Zhang
WLWenhuan Lu
Wenhuan Lu
XWXi Wei
Xi Wei
JZJialin Zhu
Jialin Zhu
HJHan Jiang
Han Jiang
RYRuiguo Yu
Ruiguo Yu
The generation-based data augmentation method can overcome the challenge caused by the imbalance of medical image data to a certain extent. However, most of the current research focus on images with unified structure which are easy to learn. What is different is that ultrasound images are structurally inadequate, making it difficult for the structure to be captured by the generative network, resulting in the generated image lacks structural legitimacy. Therefore, a Progressive Generative Adversarial Method for Structurally Inadequate Medical Image Data Augmentation is proposed in this paper, including a network and a strategy. Our Progressive Texture Generative Adversarial Network alleviates the adverse effect of completely truncating the reconstruction of structure and texture during the generation process and enhances the implicit association between structure and texture. The Image Data Augmentation Strategy based on Mask-Reconstruction overcomes data imbalance from a novel perspective, maintains the legitimacy of the structure in the generated data, as well as increases the diversity of disease data interpretably. The experiments prove the effectiveness of our method on data augmentation and image reconstruction on Structurally Inadequate Medical Image both qualitatively and quantitatively. Finally, the weakly supervised segmentation of the lesion is the additional contribution of our method.

13 April 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MYMei Yu
Mei Yu
CBChen Bai
Chen Bai
JYJian Yu
Jian Yu
MZMankun Zhao
Mankun Zhao
TXTianyi Xu
Tianyi Xu
RYRuiguo Yu
Ruiguo Yu
Knowledge representation learning achieves the automatic completion of knowledge graphs (KGs) by embedding entities into continuous low-dimensional vector space. In knowledge graph completion (KGC) tasks, the inter-dependencies and hierarchical information in KGs have gained attention. Existing methods do not well capture the latent dependencies between all components of entities and relations. To address this, we introduce the mathematical theories of octonion, a more expressive generalized form of complex number and quaternion, and propose a translation-based KGC model with octonion (TransO). TransO models entities as octonion coordinate vectors, relations as the combination of octonion component matrices and coordinate vectors, and uses specific grouping calculation rules to interact between entities and relations. In addition, since hyperbolic Poincaré space in non-Euclidean mathematics can represent hierarchical data more accurately and effectively than traditional Euclidean space, we propose a Poincaré-extended TransO model (PTransO). PTransO transforms octonion coordinate vectors into hyperbolic embeddings by exponential mapping, and integrates the Euclidean-based calculations into hyperbolic space by operations such as Möbius addition and hyperbolic distance. The experimental results of link prediction indicate that TransO outperforms other translation-based models on the WN18 benchmark, and PTransO further achieves state-of-the-art performance in low-dimensional space on the well-established WN18RR and FB15k-237 benchmarks.

24 May 2022 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
RYRuiguo Yu
Ruiguo Yu
YTYuan Tian
Yuan Tian
JGJie Gao
Jie Gao
ZLZhiqiang Liu
Zhiqiang Liu
Xi WeiXi Wei
Xi Wei
XLXuewei Li
Xuewei Li

17 June 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
MYMei Yu
Mei Yu
JGJiujiang Guo
Jiujiang Guo
JYJian Yu
Jian Yu
TXTianyi Xu
Tianyi Xu
MZMankun Zhao
Mankun Zhao
RYRuiguo Yu
Ruiguo Yu