Search Results for author: Guojie Song

Found 26 papers, 11 papers with code

Continual Learning on Dynamic Graphs via Parameter Isolation

1 code implementation23 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.

Continual Learning Graph Learning

On Structural Expressive Power of Graph Transformers

no code implementations23 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.


Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation

1 code implementation10 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.

Decision Making Session-Based Recommendations +1

Hierarchical Transformer for Scalable Graph Learning

no code implementations4 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.

Graph Learning Graph Representation Learning

LEReg: Empower Graph Neural Networks with Local Energy Regularization

no code implementations20 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.

Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily

no code implementations19 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.

Deep Molecular Representation Learning via Fusing Physical and Chemical Information

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.

molecular representation Representation Learning

Equivalent Distance Geometry Error for Molecular Conformation Comparison

1 code implementation13 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.

Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting

1 code implementation24 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 #8 on Traffic Prediction on PeMS07 (using extra training data)

Traffic Prediction

HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks

1 code implementation8 May 2021 Ziyao Li, Shuwen Yang, Guojie Song, Lingsheng Cai

Well-designed molecular representations (fingerprints) are vital to combine medical chemistry and deep learning.

molecular representation Translation

Lorentzian Graph Convolutional Networks

no code implementations15 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.

Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels

1 code implementation7 Apr 2021 Qingqing Long, Yilun Jin, Yi Wu, Guojie Song

However, the inability of GNNs to model substructures in graphs remains a significant drawback.

Graph Mining

Learning Discrete Adaptive Receptive Fields for Graph Convolutional Networks

no code implementations1 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).

Learning Node Representations from Noisy Graph Structures

no code implementations4 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.

Graph Reconstruction Node Classification

EPNE: Evolutionary Pattern Preserving Network Embedding

no code implementations24 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.

Network Embedding

Streaming Graph Neural Networks via Continual Learning

no code implementations23 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.

Continual Learning Node Classification

Graph Structural-topic Neural Network

1 code implementation25 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.

Topic Models

Multi-Component Graph Convolutional Collaborative Filtering

1 code implementation25 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.

Collaborative Filtering Recommendation Systems

GraLSP: Graph Neural Networks with Local Structural Patterns

no code implementations18 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.

Graph Representation Learning

Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets

1 code implementation11 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.

Graph Embedding Time Series +1

DANE: Domain Adaptive Network Embedding

2 code implementations3 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.

Domain Adaptation Network Embedding

Tag2Vec: Learning Tag Representations in Tag Networks

no code implementations19 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.

Network Embedding TAG

GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks

1 code implementation26 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.


SepNE: Bringing Separability to Network Embedding

no code implementations14 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.

Network Embedding

Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality

no code implementations2 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.

feature selection

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