no code implementations • 5 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.
1 code implementation • 12 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?
1 code implementation • 5 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.
1 code implementation • 25 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?
no code implementations • 14 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.
no code implementations • 5 Jun 2023 • Han Xie, Da Zheng, Jun Ma, Houyu Zhang, Vassilis N. Ioannidis, Xiang Song, Qing Ping, Sheng Wang, Carl Yang, Yi Xu, Belinda Zeng, Trishul Chilimbi
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain.
no code implementations • 1 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.
1 code implementation • 27 Feb 2023 • Arpandeep Khatua, Vikram Sharma Mailthody, Bhagyashree Taleka, Tengfei Ma, Xiang Song, Wen-mei Hwu
Most existing public datasets for GNNs are relatively small, which limits the ability of GNNs to generalize to unseen data.
1 code implementation • 24 Feb 2023 • Shichang Zhang, Jiani Zhang, Xiang Song, Soji Adeshina, Da Zheng, Christos Faloutsos, Yizhou Sun
However, GNN explanation for link prediction (LP) is lacking in the literature.
no code implementations • 18 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.
no code implementations • 16 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.
no code implementations • 25 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.
no code implementations • 22 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.
no code implementations • 24 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 .
2 code implementations • 28 Mar 2022 • Hongkuan Zhou, Da Zheng, Israt Nisa, Vasileios Ioannidis, Xiang Song, George Karypis
Our temporal parallel sampler achieves an average of 173x speedup on a multi-core CPU compared with the baselines.
no code implementations • 23 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.
Ranked #1 on Link Property Prediction on ogbl-citation2
no code implementations • 10 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.
1 code implementation • 11 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.
no code implementations • AACL (knlp) 2020 • Colby Wise, Vassilis N. Ioannidis, Miguel Romero Calvo, Xiang Song, George Price, Ninad Kulkarni, Ryan Brand, Parminder Bhatia, George Karypis
Finally, we propose a document similarity engine that leverages low-dimensional graph embeddings from the CKG with semantic embeddings for similar article retrieval.
no code implementations • 21 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.
1 code implementation • 18 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
no code implementations • 2 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.
7 code implementations • 3 Sep 2019 • Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, Xiang Song, Jinjing Zhou, Chao Ma, Lingfan Yu, Yu Gai, Tianjun Xiao, Tong He, George Karypis, Jinyang Li, Zheng Zhang
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs.
Ranked #35 on Node Classification on Cora