46 citations · 83 across the 14 of their papers we have counts for
14 papers
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF
Wei Chen, Guanghui Zhu, Yafei Li +2
Reinforcement learning from human feedback (RLHF) with preference-based reward models often exhibits unstable training dynamics. A key contributing factor is that standard RLHF rel…
DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization
Tao Tao, Guanghui Zhu, Lang Guo +3
Prompt Optimization has emerged as a crucial approach due to its capabilities in steering Large Language Models to solve various tasks. However, current works mainly rely on the ra…
BOASF: A Unified Framework for Speeding up Automatic Machine Learning via Adaptive Successive Filtering
Guanghui Zhu, Xin Fang, Feng Cheng +4
Machine learning has been making great success in many application areas. However, for the non-expert practitioners, it is always very challenging to address a machine learning tas…
PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs
Tongzhou Yu, Zhuhao Zhang, Guanghui Zhu +3
Parameter Efficient Fine-Tuning (PEFT) methods have emerged as effective and promising approaches for fine-tuning pre-trained language models. Compared with Full parameter Fine-Tun…
SA-GNAS: Seed Architecture Expansion for Efficient Large-scale Graph Neural Architecture Search
Guanghui Zhu, Zipeng Ji, Jingyan Chen +3
GNAS (Graph Neural Architecture Search) has demonstrated great effectiveness in automatically designing the optimal graph neural architectures for multiple downstream tasks, such a…
Simple and Efficient Partial Graph Adversarial Attack: A New Perspective
Guanghui Zhu, Mengyu Chen, Chunfeng Yuan +1
As the study of graph neural networks becomes more intensive and comprehensive, their robustness and security have received great research interest. The existing global attack meth…
HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networks
Guanghui Zhu, Zhennan Zhu, Hongyang Chen +2
Heterogeneous graph neural networks (GNNs) have been successful in handling heterogeneous graphs. In existing heterogeneous GNNs, meta-path plays an essential role. However, recent…
AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network
Guanghui Zhu, Zhennan Zhu, Wenjie Wang +3
Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural netw…
A2: Efficient Automated Attacker for Boosting Adversarial Training
Zhuoer Xu, Guanghui Zhu, Changhua Meng +5
Based on the significant improvement of model robustness by AT (Adversarial Training), various variants have been proposed to further boost the performance. Well-recognized methods…
Knowledge-enhanced Black-box Attacks for Recommendations
Jingfan Chen, Wenqi Fan, Guanghui Zhu +4
Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles…
Transition Relation Aware Self-Attention for Session-based Recommendation
Guanghui Zhu, Haojun Hou, Jingfan Chen +2
Session-based recommendation is a challenging problem in the real-world scenes, e.g., ecommerce, short video platforms, and music platforms, which aims to predict the next click ac…
UniGPS: A Unified Programming Framework for Distributed Graph Processing
Zhaokang Wang, Junhong Li, Yifan Qi +3
The industry and academia have proposed many distributed graph processing systems. However, the existing systems are not friendly enough for users like data analysts and algorithm…
DIFER: Differentiable Automated Feature Engineering
Guanghui Zhu, Zhuoer Xu, Xu Guo +2
Feature engineering, a crucial step of machine learning, aims to extract useful features from raw data to improve data quality. In recent years, great efforts have been devoted to…
Semi-supervised Embedding Learning for High-dimensional Bayesian Optimization
Jingfan Chen, Guanghui Zhu, Chunfeng Yuan +1
Bayesian optimization is a broadly applied methodology to optimize the expensive black-box function. Despite its success, it still faces the challenge from the high-dimensional sea…