7 citations · 9 across the 8 of their papers we have counts for
8 papers
Towards an On-device Agent for Text Rewriting
Yun Zhu, Yinxiao Liu, Felix Stahlberg +7
Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting. Nonetheless, the large sizes of these models make them impractical for on-device inferenc…
MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning
Yun Zhu, Haizhou Shi, Zhenshuo Zhang +1
In this work, we investigate the problem of out-of-distribution (OOD) generalization for unsupervised learning methods on graph data. This scenario is particularly challenging beca…
Structure-Aware Group Discrimination with Adaptive-View Graph Encoder: A Fast Graph Contrastive Learning Framework
Zhenshuo Zhang, Yun Zhu, Haizhou Shi +1
Albeit having gained significant progress lately, large-scale graph representation learning remains expensive to train and deploy for two main reasons: (i) the repetitive computati…
SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference
Boren Hu, Yun Zhu, Jiacheng Li +1
Dynamic early exiting has been proven to improve the inference speed of the pre-trained language model like BERT. However, all samples must go through all consecutive layers before…
SGL-PT: A Strong Graph Learner with Graph Prompt Tuning
Yun Zhu, Jianhao Guo, Siliang Tang
Recently, much exertion has been paid to design graph self-supervised methods to obtain generalized pre-trained models, and adapt pre-trained models onto downstream tasks through f…
RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning
Yun Zhu, Jianhao Guo, Fei Wu +1
Graph contrastive learning has gained significant progress recently. However, existing works have rarely explored non-aligned node-node contrasting. In this paper, we propose a nov…
Active Learning for Product Type Ontology Enhancement in E-commerce
Yun Zhu, Sayyed M. Zahiri, Jiaqi Wang +2
Entity-based semantic search has been widely adopted in modern search engines to improve search accuracy by understanding users' intent. In e-commerce, an accurate and complete pro…
Semantic Similarity Strategies for Job Title Classification
Yun Zhu, Faizan Javed, Ozgur Ozturk
Automatic and accurate classification of items enables numerous downstream applications in many domains. These applications can range from faceted browsing of items to product reco…