Search Results for author: Xiang Song

Found 23 papers, 8 papers with code

KGExplainer: Towards Exploring Connected Subgraph Explanations for Knowledge Graph Completion

no code implementations5 Apr 2024 Tengfei Ma, Xiang Song, Wen Tao, Mufei Li, Jiani Zhang, Xiaoqin Pan, Jianxin Lin, Bosheng Song, Xiangxiang Zeng

Knowledge graph completion (KGC) aims to alleviate the inherent incompleteness of knowledge graphs (KGs), which is a critical task for various applications, such as recommendations on the web.

Knowledge Graph Embedding

NetInfoF Framework: Measuring and Exploiting Network Usable Information

1 code implementation12 Feb 2024 Meng-Chieh Lee, Haiyang Yu, Jian Zhang, Vassilis N. Ioannidis, Xiang Song, Soji Adeshina, Da Zheng, Christos Faloutsos

Given a node-attributed graph, and a graph task (link prediction or node classification), can we tell if a graph neural network (GNN) will perform well?

Link Prediction Node Classification

On the Initialization of Graph Neural Networks

1 code implementation5 Dec 2023 Jiahang Li, Yakun Song, Xiang Song, David Paul Wipf

In this paper, we analyze the variance of forward and backward propagation across GNN layers and show that the variance instability of GNN initializations comes from the combined effect of the activation function, hidden dimension, graph structure and message passing.

Graph Classification Graph Representation Learning +2

TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning

no code implementations25 Sep 2023 Jing Zhu, Xiang Song, Vassilis N. Ioannidis, Danai Koutra, Christos Faloutsos

How can we enhance the node features acquired from Pretrained Models (PMs) to better suit downstream graph learning tasks?

Domain Adaptation Graph Learning +2

DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training

no code implementations14 Jul 2023 Hongkuan Zhou, Da Zheng, Xiang Song, George Karypis, Viktor Prasanna

Evenworse, the tremendous overhead to synchronize the node memory make it impractical to be deployed to distributed GPU clusters.

Graph Representation Learning

Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices

no code implementations1 Jun 2023 Jing Zhu, YuHang Zhou, Vassilis N. Ioannidis, Shengyi Qian, Wei Ai, Xiang Song, Danai Koutra

While Graph Neural Networks (GNNs) are remarkably successful in a variety of high-impact applications, we demonstrate that, in link prediction, the common practices of including the edges being predicted in the graph at training and/or test have outsized impact on the performance of low-degree nodes.

Link Prediction Node Classification

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training

no code implementations18 Jan 2023 Kezhao Huang, Haitian Jiang, Minjie Wang, Guangxuan Xiao, David Wipf, Xiang Song, Quan Gan, Zengfeng Huang, Jidong Zhai, Zheng Zhang

A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU.

Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures

no code implementations16 Jan 2023 Kun Wu, Mert Hidayetoğlu, Xiang Song, Sitao Huang, Da Zheng, Israt Nisa, Wen-mei Hwu

Relational graph neural networks (RGNNs) are graph neural networks with dedicated structures for modeling the different types of nodes and edges in heterogeneous graphs.

8k C++ code +1

Refined Edge Usage of Graph Neural Networks for Edge Prediction

no code implementations25 Dec 2022 Jiarui Jin, Yangkun Wang, Weinan Zhang, Quan Gan, Xiang Song, Yong Yu, Zheng Zhang, David Wipf

However, existing methods lack elaborate design regarding the distinctions between two tasks that have been frequently overlooked: (i) edges only constitute the topology in the node classification task but can be used as both the topology and the supervisions (i. e., labels) in the edge prediction task; (ii) the node classification makes prediction over each individual node, while the edge prediction is determinated by each pair of nodes.

Link Prediction Node Classification

Efficient and effective training of language and graph neural network models

no code implementations22 Jun 2022 Vassilis N. Ioannidis, Xiang Song, Da Zheng, Houyu Zhang, Jun Ma, Yi Xu, Belinda Zeng, Trishul Chilimbi, George Karypis

The effectiveness in our framework is achieved by applying stage-wise fine-tuning of the BERT model first with heterogenous graph information and then with a GNN model.

Edge Classification Language Modelling +1

ColdGuess: A General and Effective Relational Graph Convolutional Network to Tackle Cold Start Cases

no code implementations24 May 2022 Bo He, Xiang Song, Vincent Gao, Christos Faloutsos

It outperforms the lightgbm2 by up to 34 pcp ROC-AUC in a cold start case when a new seller sells a new product .

Network In Graph Neural Network

no code implementations23 Nov 2021 Xiang Song, Runjie Ma, Jiahang Li, Muhan Zhang, David Paul Wipf

However, wider hidden layers can easily lead to overfitting, and incrementally adding more GNN layers can potentially result in over-smoothing. In this paper, we present a model-agnostic methodology, namely Network In Graph Neural Network (NGNN ), that allows arbitrary GNN models to increase their model capacity by making the model deeper.

Fraud Detection Link Prediction +1

Graph Neural Network Training with Data Tiering

no code implementations10 Nov 2021 Seung Won Min, Kun Wu, Mert Hidayetoğlu, JinJun Xiong, Xiang Song, Wen-mei Hwu

With our data tiering method, we additionally provide a new data placement and access strategy to further minimize the CPU-GPU communication overhead.

Fraud Detection

DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs

1 code implementation11 Oct 2020 Da Zheng, Chao Ma, Minjie Wang, Jinjing Zhou, Qidong Su, Xiang Song, Quan Gan, Zheng Zhang, George Karypis

To minimize the overheads associated with distributed computations, DistDGL uses a high-quality and light-weight min-cut graph partitioning algorithm along with multiple balancing constraints.

Fraud Detection graph partitioning

Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning

no code implementations21 May 2020 Xiangxiang Zeng, Xiang Song, Tengfei Ma, Xiaoqin Pan, Yadi Zhou, Yuan Hou, Zheng Zhang, George Karypis, Feixiong Cheng

While this study, by no means recommends specific drugs, it demonstrates a powerful deep learning methodology to prioritize existing drugs for further investigation, which holds the potential of accelerating therapeutic development for COVID-19.

DGL-KE: Training Knowledge Graph Embeddings at Scale

1 code implementation18 Apr 2020 Da Zheng, Xiang Song, Chao Ma, Zeyuan Tan, Zihao Ye, Jin Dong, Hao Xiong, Zheng Zhang, George Karypis

Experiments on knowledge graphs consisting of over 86M nodes and 338M edges show that DGL-KE can compute embeddings in 100 minutes on an EC2 instance with 8 GPUs and 30 minutes on an EC2 cluster with 4 machines with 48 cores/machine.

Distributed, Parallel, and Cluster Computing

A Novel Graph based Trajectory Predictor with Pseudo Oracle

no code implementations2 Feb 2020 Biao Yang, Guocheng Yan, Pin Wang, Ching-Yao Chan, Xiang Song, Yang Chen

Recent studies focus on modeling pedestrians' motion patterns with recurrent neural networks, capturing social interactions with pooling-based or graph-based methods, and handling future uncertainties by using random Gaussian noise as the latent variable.

Graph Attention Pedestrian Trajectory Prediction +2

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