no code implementations • 24 May 2025 • Haonan Dong, Wenhao Zhu, Guojie Song, Liang Wang
Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method validated across NLP and CV domains.
no code implementations • 19 May 2025 • Wenhao Zhu, Yuhang Xie, Guojie Song, Xin Zhang
The rapid evolution of large language models (LLMs) has revolutionized various fields, including the identification and discovery of human values within text data.
1 code implementation • 13 May 2025 • Haoran Ye, Jing Jin, Yuhang Xie, Xin Zhang, Guojie Song
The rapid advancement of large language models (LLMs) has outpaced traditional evaluation methodologies.
no code implementations • 4 Feb 2025 • Haoran Ye, Tianze Zhang, Yuhang Xie, Liyuan Zhang, Yuanyi Ren, Xin Zhang, Guojie Song
Despite growing efforts in evaluating, understanding, and aligning LLM values, a psychologically grounded LLM value system remains underexplored.
1 code implementation • 25 Jan 2025 • Qin Chen, Liang Wang, Bo Zheng, Guojie Song
This paper identifies two key challenges in adapting graph prompting methods for complex graphs: (1) adapting the model to new distributions in downstream tasks to mitigate pre-training and fine-tuning discrepancies from heterophily and (2) customizing prompts for hop-specific node requirements.
1 code implementation • 10 Jan 2025 • Yunbo Hou, Haoran Ye, Shuwen Yang, Yingxue Zhang, Siyuan Xu, Guojie Song
Global placement, a critical step in designing the physical layout of computer chips, is essential to optimize chip performance.
1 code implementation • 18 Sep 2024 • Haoran Ye, Yuhang Xie, Yuanyi Ren, Hanjun Fang, Xin Zhang, Guojie Song
Human values and their measurement are long-standing interdisciplinary inquiry.
1 code implementation • 6 Jun 2024 • Yuanyi Ren, Haoran Ye, Hanjun Fang, Xin Zhang, Guojie Song
This work introduces ValueBench, the first comprehensive psychometric benchmark for evaluating value orientations and value understanding in LLMs.
1 code implementation • 4 Jun 2024 • Yunbo Hou, Haoran Ye, Yingxue Zhang, Siyuan Xu, Guojie Song
Placement is a critical and challenging step of modern chip design, with routability being an essential indicator of placement quality.
no code implementations • 6 May 2024 • Wenhao Zhu, Guojie Song, Liang Wang, Shaoguo Liu
Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power.
3 code implementations • 2 Feb 2024 • Haoran Ye, Jiarui Wang, Zhiguang Cao, Federico Berto, Chuanbo Hua, Haeyeon Kim, Jinkyoo Park, Guojie Song
The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design.
3 code implementations • 29 Jun 2023 • Federico Berto, Chuanbo Hua, Junyoung Park, Laurin Luttmann, Yining Ma, Fanchen Bu, Jiarui Wang, Haoran Ye, Minsu Kim, Sanghyeok Choi, Nayeli Gast Zepeda, André Hottung, Jianan Zhou, Jieyi Bi, Yu Hu, Fei Liu, Hyeonah Kim, Jiwoo Son, Haeyeon Kim, Davide Angioni, Wouter Kool, Zhiguang Cao, Qingfu Zhang, Joungho Kim, Jie Zhang, Kijung Shin, Cathy Wu, Sungsoo Ahn, Guojie Song, Changhyun Kwon, Kevin Tierney, Lin Xie, Jinkyoo Park
To fill this gap, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 23 state-of-the-art methods and more than 20 CO problems.
no code implementations • 23 May 2023 • Wenhao Zhu, Tianyu Wen, Guojie Song, Liang Wang, Bo Zheng
Graph Transformer has recently received wide attention in the research community with its outstanding performance, yet its structural expressive power has not been well analyzed.
1 code implementation • 23 May 2023 • Peiyan Zhang, Yuchen Yan, Chaozhuo Li, Senzhang Wang, Xing Xie, Guojie Song, Sunghun Kim
Dynamic graph learning methods commonly suffer from the catastrophic forgetting problem, where knowledge learned for previous graphs is overwritten by updates for new graphs.
1 code implementation • 10 May 2023 • Di Jin, Luzhi Wang, Yizhen Zheng, Guojie Song, Fei Jiang, Xiang Li, Wei Lin, Shirui Pan
We design a dual-intent network to learn user intent from an attention mechanism and the distribution of historical data respectively, which can simulate users' decision-making process in interacting with a new item.
no code implementations • 4 May 2023 • Wenhao Zhu, Tianyu Wen, Guojie Song, Xiaojun Ma, Liang Wang
Graph Transformer is gaining increasing attention in the field of machine learning and has demonstrated state-of-the-art performance on benchmarks for graph representation learning.
no code implementations • 20 Mar 2022 • Xiaojun Ma, Hanyue Chen, Guojie Song
With Intra-Energy Reg, we strengthen the message passing within each part, which is beneficial for getting more useful information.
no code implementations • 19 Mar 2022 • Xiaojun Ma, Qin Chen, Yuanyi Ren, Guojie Song, Liang Wang
These experiments show the excellent expressive power of MWGNN in dealing with graph data with various distributions.
no code implementations • NeurIPS 2021 • Shuwen Yang, Ziyao Li, Guojie Song, Lingsheng Cai
To push the boundaries of molecular representation learning, we present PhysChem, a novel neural architecture that learns molecular representations via fusing physical and chemical information of molecules.
1 code implementation • 13 Nov 2021 • Shuwen Yang, Tianyu Wen, Ziyao Li, Guojie Song
Straight-forward conformation generation models, which generate 3-D structures directly from input molecular graphs, play an important role in various molecular tasks with machine learning, such as 3D-QSAR and virtual screening in drug design.
1 code implementation • 24 Jun 2021 • Zheng Fang, Qingqing Long, Guojie Song, Kunqing Xie
However, the representation ability of such models is limited due to: (1) shallow GNNs are incapable to capture long-range spatial correlations, (2) only spatial connections are considered and a mass of semantic connections are ignored, which are of great importance for a comprehensive understanding of traffic networks.
Ranked #5 on
Traffic Prediction
on LargeST
1 code implementation • 8 May 2021 • Ziyao Li, Shuwen Yang, Guojie Song, Lingsheng Cai
Well-designed molecular representations (fingerprints) are vital to combine medical chemistry and deep learning.
no code implementations • 15 Apr 2021 • Yiding Zhang, Xiao Wang, Chuan Shi, Nian Liu, Guojie Song
We also find that the performance of some hyperbolic GCNs can be improved by simply replacing the graph operations with those we defined in this paper.
1 code implementation • 7 Apr 2021 • Qingqing Long, Yilun Jin, Yi Wu, Guojie Song
However, the inability of GNNs to model substructures in graphs remains a significant drawback.
no code implementations • ICLR 2021 • Ziyao Li, Shuwen Yang, Guojie Song, Lingsheng Cai
Well-designed molecular representations (fingerprints) are vital to combine medical chemistry and deep learning.
no code implementations • 1 Jan 2021 • Xiaojun Ma, Ziyao Li, Lingjun Xu, Guojie Song, Yi Li, Chuan Shi
To address this weakness, we introduce a novel framework of conducting graph convolutions, where nodes are discretely selected among multi-hop neighborhoods to construct adaptive receptive fields (ARFs).
no code implementations • 4 Dec 2020 • Junshan Wang, Ziyao Li, Qingqing Long, Weiyu Zhang, Guojie Song, Chuan Shi
Since noises are often unknown on real graphs, we design two generators, namely a graph generator and a noise generator, to identify normal structures and noises in an unsupervised setting.
no code implementations • 24 Sep 2020 • Junshan Wang, Yilun Jin, Guojie Song, Xiaojun Ma
In this paper, we propose EPNE, a temporal network embedding model preserving evolutionary patterns of the local structure of nodes.
no code implementations • 23 Sep 2020 • Junshan Wang, Guojie Song, Yi Wu, Liang Wang
In this paper, we propose a streaming GNN model based on continual learning so that the model is trained incrementally and up-to-date node representations can be obtained at each time step.
1 code implementation • 25 Jun 2020 • Qingqing Long, Yilun Jin, Guojie Song, Yi Li, Wei. Lin
Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently.
1 code implementation • 25 Nov 2019 • Xiao Wang, Ruijia Wang, Chuan Shi, Guojie Song, Qingyong Li
The interactions of users and items in recommender system could be naturally modeled as a user-item bipartite graph.
no code implementations • 18 Nov 2019 • Yilun Jin, Guojie Song, Chuan Shi
Specifically, we capture local graph structures via random anonymous walks, powerful and flexible tools that represent structural patterns.
1 code implementation • 11 Nov 2019 • Ziqiang Cheng, Yang Yang, Wei Wang, Wenjie Hu, Yueting Zhuang, Guojie Song
Time series modeling has attracted extensive research efforts; however, achieving both reliable efficiency and interpretability from a unified model still remains a challenging problem.
2 code implementations • 3 Jun 2019 • Yizhou Zhang, Guojie Song, Lun Du, Shu-wen Yang, Yilun Jin
Recent works reveal that network embedding techniques enable many machine learning models to handle diverse downstream tasks on graph structured data.
no code implementations • 19 Apr 2019 • Junshan Wang, Zhicong Lu, Guojie Song, Yue Fan, Lun Du, Wei. Lin
Network embedding is a method to learn low-dimensional representation vectors for nodes in complex networks.
1 code implementation • 26 Feb 2019 • Ziyao Li, Liang Zhang, Guojie Song
Graph Convolutional Networks (GCNs) have proved to be a most powerful architecture in aggregating local neighborhood information for individual graph nodes.
no code implementations • 14 Nov 2018 • Ziyao Li, Liang Zhang, Guojie Song
We further propose SepNE, a simple and flexible network embedding algorithm which independently learns representations for different subsets of nodes in separated processes.
no code implementations • 2 Nov 2017 • Zhongang Qi, Tianchun Wang, Guojie Song, Weisong Hu, Xi Li, Zhongfei, Zhang
The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing.