Search Results for author: Yankai Chen

Found 11 papers, 1 papers with code

HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval

no code implementations14 Jan 2024 Zexuan Qiu, Jiahong Liu, Yankai Chen, Irwin King

Existing unsupervised deep product quantization methods primarily aim for the increased similarity between different views of the identical image, whereas the delicate multi-level semantic similarities preserved between images are overlooked.

Contrastive Learning Image Retrieval +4

Hyperbolic Representation Learning: Revisiting and Advancing

1 code implementation15 Jun 2023 Menglin Yang, Min Zhou, Rex Ying, Yankai Chen, Irwin King

To address this, we propose a simple yet effective method, hyperbolic informed embedding (HIE), by incorporating cost-free hierarchical information deduced from the hyperbolic distance of the node to origin (i. e., induced hyperbolic norm) to advance existing \hlms.

Representation Learning

Bipartite Graph Convolutional Hashing for Effective and Efficient Top-N Search in Hamming Space

no code implementations1 Apr 2023 Yankai Chen, Yixiang Fang, Yifei Zhang, Irwin King

We propose an end-to-end Bipartite Graph Convolutional Hashing approach, namely BGCH, which consists of three novel and effective modules: (1) adaptive graph convolutional hashing, (2) latent feature dispersion, and (3) Fourier serialized gradient estimation.

Retrieval

Knowledge-aware Neural Networks with Personalized Feature Referencing for Cold-start Recommendation

no code implementations28 Sep 2022 Xinni Zhang, Yankai Chen, Cuiyun Gao, Qing Liao, Shenglin Zhao, Irwin King

Incorporating knowledge graphs (KGs) as side information in recommendation has recently attracted considerable attention.

Knowledge Graphs

Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation

no code implementations5 Sep 2021 Yankai Chen, Yaming Yang, Yujing Wang, Jing Bai, Xiangchen Song, Irwin King

However, simply integrating KGs in current KG-based RS models is not necessarily a guarantee to improve the recommendation performance, which may even weaken the holistic model capability.

Click-Through Rate Prediction Knowledge-Aware Recommendation +1

Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation

no code implementations14 Aug 2021 Yankai Chen, Menglin Yang, Yingxue Zhang, Mengchen Zhao, Ziqiao Meng, Jianye Hao, Irwin King

Aiming to alleviate data sparsity and cold-start problems of traditional recommender systems, incorporating knowledge graphs (KGs) to supplement auxiliary information has recently gained considerable attention.

Knowledge-Aware Recommendation Knowledge Graphs

A Literature Review of Recent Graph Embedding Techniques for Biomedical Data

no code implementations17 Jan 2021 Yankai Chen, Yaozu Wu, Shicheng Ma, Irwin King

With the rapid development of biomedical software and hardware, a large amount of relational data interlinking genes, proteins, chemical components, drugs, diseases, and symptoms has been collected for modern biomedical research.

Graph Embedding

Cannot find the paper you are looking for? You can Submit a new open access paper.