Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperJuly 2024
TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information RetrievalJuly 2024, Pages 2662–2666https://doi.org/10.1145/3626772.3657978How can we enhance the node features acquired from Pretrained Models (PMs) to better suit downstream graph learning tasks? Graph Neural Networks (GNNs) have become the state-of-the-art approach for many high-impact, real-world graph applications. For ...
FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
- Kezhao Huang,
- Haitian Jiang,
- Minjie Wang,
- Guangxuan Xiao,
- David Wipf,
- Xiang Song,
- Quan Gan,
- Zengfeng Huang,
- Jidong Zhai,
- Zheng Zhang
Proceedings of the VLDB Endowment (PVLDB), Volume 17, Issue 6Pages 1473–1486https://doi.org/10.14778/3648160.3648184A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU. Due to limited GPU memory, expensive data movement is necessary to facilitate the storage of these features on ...
- research-articleApril 2024
Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures
ASPLOS '24: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3April 2024, Pages 528–544https://doi.org/10.1145/3620666.3651322Relational graph neural networks (RGNNs) are graph neural networks with dedicated structures for modeling the different types of nodes and edges in heterogeneous graphs. While RGNNs have been increasingly adopted in many real-world applications due to ...
- research-articleMarch 2024
Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningMarch 2024, Pages 994–1002https://doi.org/10.1145/3616855.3635786While 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 ...
- research-articleFebruary 2024
A two-stage stochastic model for a multi-objective blood platelet supply chain network design problem incorporating frozen platelets
Computers and Industrial Engineering (CINE), Volume 185, Issue CNov 2023https://doi.org/10.1016/j.cie.2023.109651Highlights- Propose a two-stage stochastic programming model for a platelet supply chain problem incorporating frozen platelets.
- An extended goal programming model is built based on the proposed 2SSP model.
- Apply a top-down forecasting ...
Platelet supply chain (PLT SC) management is always a challenging task for healthcare systems due to the nature of platelets (PLTs). PLTs have an extremely short shelf life and their demand is highly uncertain, which may lead to a high percentage ...
-
DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training
SC '23: Proceedings of the International Conference for High Performance Computing, Networking, Storage and AnalysisNovember 2023, Article No.: 39, Pages 1–12https://doi.org/10.1145/3581784.3607056Memory-based Temporal Graph Neural Networks are powerful tools in dynamic graph representation learning and have demonstrated superior performance in many real-world applications. However, their node memory favors smaller batch sizes to capture more ...
- research-articleAugust 2023
IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 4284–4295https://doi.org/10.1145/3580305.3599843Graph neural networks (GNNs) have shown high potential for a variety of real-world, challenging applications, but one of the major obstacles in GNN research is the lack of large-scale flexible datasets. Most existing public datasets for GNNs are ...
- research-articleAugust 2023
Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
- 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
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 5270–5281https://doi.org/10.1145/3580305.3599833Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of ...
- abstractAugust 2023
GraphStorm an Easy-to-use and Scalable Graph Neural Network Framework: From Beginners to Heroes
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2023, Pages 5790–5791https://doi.org/10.1145/3580305.3599179Applying Graph Neural Networks (GNNs) to real-world problems is challenging for machine learning (ML) practitioners due to two major obstacles. The first hurdle is the high barrier to learn programming GNNs from scratch. The second challenge lies in ...
- research-articleJuly 2023
On the initialization of graph neural networks
ICML'23: Proceedings of the 40th International Conference on Machine LearningJuly 2023, Article No.: 822, Pages 19911–19931Graph Neural Networks (GNNs) have displayed considerable promise in graph representation learning across various applications. The core learning process requires the initialization of model weight matrices within each GNN layer, which is typically ...
- research-articleJune 2023
Domain Incremental Object Detection Based on Feature Space Topology Preserving Strategy
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 34, Issue 1Jan. 2024, Pages 424–437https://doi.org/10.1109/TCSVT.2023.3285263Object detection with the capacity to incrementally adapt to new domains is a crucial yet relatively under-explored research topic. The catastrophic forgetting problem presents a significant challenge to achieve this goal, where the model’s ...
- research-articleApril 2023
PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction
WWW '23: Proceedings of the ACM Web Conference 2023April 2023, Pages 3784–3793https://doi.org/10.1145/3543507.3583511Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN)...
- research-articleMarch 2023
Semantic Knowledge Guided Class-Incremental Learning
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 33, Issue 10Oct. 2023, Pages 5921–5931https://doi.org/10.1109/TCSVT.2023.3262739Driven by practical needs, research on Class-Incremental Learning (CIL) has received more and more attentions in recent years. A technical challenge to be conquered by CIL methods is the catastrophic forgetting problem, where the model’s ...
- research-articleFebruary 2023
DSP: Efficient GNN Training with Multiple GPUs
PPoPP '23: Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel ProgrammingFebruary 2023, Pages 392–404https://doi.org/10.1145/3572848.3577528Jointly utilizing multiple GPUs to train graph neural networks (GNNs) is crucial for handling large graphs and achieving high efficiency. However, we find that existing systems suffer from high communication costs and low GPU utilization due to improper ...
- research-articleAugust 2022
Distributed Hybrid CPU and GPU training for Graph Neural Networks on Billion-Scale Heterogeneous Graphs
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2022, Pages 4582–4591https://doi.org/10.1145/3534678.3539177Graph neural networks (GNN) have shown great success in learn- ing from graph-structured data. They are widely used in various applications, such as recommendation, fraud detection, and search. In these domains, the graphs are typically large and ...
- research-articleAugust 2022
Graph Neural Network Training and Data Tiering
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAugust 2022, Pages 3555–3565https://doi.org/10.1145/3534678.3539038Graph Neural Networks (GNNs) have shown success in learning from graph-structured data, with applications to fraud detection, recommendation, and knowledge graph reasoning. However, training GNN efficiently is challenging because: 1) GPU memory capacity ...
- research-articleJune 2022
Enabling Trimap-Free Image Matting With a Frequency-Guided Saliency-Aware Network via Joint Learning
IEEE Transactions on Multimedia (TOM), Volume 252023, Pages 4868–4879https://doi.org/10.1109/TMM.2022.3183403This paper presents a strategic approach to tackling trimap-free natural image matting. Specifically, to address the false detection issue of existing trimap-free matting algorithms when the foreground object is not uniquely defined, we design a novel ...
TGL: a general framework for temporal GNN training on billion-scale graphs
Proceedings of the VLDB Endowment (PVLDB), Volume 15, Issue 8Pages 1572–1580https://doi.org/10.14778/3529337.3529342Many real world graphs contain time domain information. Temporal Graph Neural Networks capture temporal information as well as structural and contextual information in the generated dynamic node embeddings. Researchers have shown that these embeddings ...
- research-articleSeptember 2021
A Back-Pressure-Based Model With Fixed Phase Sequences for Traffic Signal Optimization Under Oversaturated Networks
IEEE Transactions on Intelligent Transportation Systems (ITS-TRANSACTIONS), Volume 22, Issue 9Sept. 2021, Pages 5577–5588https://doi.org/10.1109/TITS.2020.2987917Traffic signal control under oversaturated conditions presents a major challenge in metropolitan transportation networks. Previous works have demonstrated the ability of back-pressure methods to maximize network throughput and guarantee network stability. ...
- tutorialMarch 2021
Scalable Graph Neural Networks with Deep Graph Library
WSDM '21: Proceedings of the 14th ACM International Conference on Web Search and Data MiningMarch 2021, Pages 1141–1142https://doi.org/10.1145/3437963.3441663Learning from graph and relational data plays a major role in many applications including social network analysis, marketing, e-commerce, information retrieval, knowledge modeling, medical and biological sciences, engineering, and others. Recently, ...