An official website of the United States government
Memory-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 dependencies in graph events and needs to be maintained synchronously across all trainers. As a result, existing frameworks suffer from accuracy loss when scaling to multiple GPUs. Even worse, the tremendous overhead of synchronizing the node memory makes it impractical to deploy the solution in GPU clusters. In this work, we propose DistTGL — an efficient and scalable solution to train memory-based TGNNs on distributed GPU clusters. DistTGL has three improvements over existing solutions: an enhanced TGNN model, a novel training algorithm, and an optimized system. In experiments, DistTGL achieves near-linear convergence speedup, outperforming the state-of-the-art single-machine method by 14.5% in accuracy and 10.17× in training throughput.
more »
« less
Enhanced Knowledge Graph Attention Networks for Efficient Graph Learning
This paper introduces an innovative design for Enhanced Knowledge Graph Attention Networks (EKGAT), focusing on improving representation learning for graph-structured data. By integrating TransformerConv layers, the proposed EKGAT model excels in capturing complex node relationships compared to traditional KGAT models. Additionally, our EKGAT model integrates disentanglement learning techniques to segment entity representations into independent components, thereby capturing various semantic aspects more effectively. Comprehensive experiments on the Cora, PubMed, and Amazon datasets reveal substantial improvements in node classification accuracy and convergence speed. The incorporation of TransformerConv layers significantly accelerates the convergence of the training loss function while either maintaining or enhancing accuracy, which is particularly advantageous for large-scale, real-time applications. Results from t-SNE and PCA analyses vividly illustrate the superior embedding separability achieved by our model, underscoring its enhanced representation capabilities. These findings highlight the potential of EKGAT to advance graph analytics and network science, providing robust, scalable solutions for a wide range of applications, from recommendation systems and social network analysis to biomedical data interpretation and real-time big data processing.
more »
« less
- Award ID(s):
- 2109988
- PAR ID:
- 10561973
- Publisher / Repository:
- 28th Annual IEEE High Performance Extreme Computing Conference (HPEC)
- Date Published:
- Format(s):
- Medium: X
- Location:
- Virtual
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Network embedding has been an effective tool to analyze heterogeneous networks (HNs) by representing nodes in a low-dimensional space. Although many recent methods have been proposed for representation learning of HNs, there is still much room for improvement. Random walks based methods are currently popular methods to learn network embedding; however, they are random and limited by the length of sampled walks, and have dif culty capturing network structural information. Some recent researches proposed using meta paths to express the sample relationship in HNs. Another popular graph learning model, the graph convolutional network (GCN) is known to be capable of better exploitation of network topology, but the current design of GCN is intended for homogenous networks. This paper proposes a novel combination of meta-graph and graph convolution, the meta-graph based graph convolutional networks (MGCN). To fully capture the complex long semantic information, MGCN utilizes different meta-graphs in HNs. As different meta-graphs express different semantic relationships, MGCN learns the weights of different meta-graphs to make up for the loss of semantics when applying GCN. In addition, we improve the current convolution design by adding node self-signi cance. To validate our model in learning feature representation, we present comprehensive experiments on four real-world datasets and two representation tasks: classi cation and link prediction. WMGCN's representations can improve accuracy scores by up to around 10% in comparison to other popular representation learning models. What's more, WMGCN'feature learning outperforms other popular baselines. The experimental results clearly show our model is superior over other state-of-the-art representation learning algorithms.more » « less
-
Jihe Wang, Yi He (Ed.)Influence propagation is a network phenomenon governing how information is diffused in a network. With the advent of deep learning, there has been growing interest in applying graph neural networks to extract salient feature representation of the nodes for a variety of network mining tasks, such as forecasting the virality of information cascade. Given the importance of social influence, this paper presents a novel deep learning framework called IP-GNN for simulating the information propagation process in a complex network and learning a node representation that embeds information about the diffusion process under the linear threshold model. Our framework employs a modified graph convolutional network architecture with adaptive diffusion kernel to capture long-range propagation of information along with an entropy-regularized mixture of loss functions to ensure accurate prediction and faster convergence of the learning algorithm. Experimental results on 4 real-world datasets show that the model accurately mimics the output of the linear threshold model, achieving an average accuracy that exceeds 90\% on all datasets.more » « less
-
Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating information of its neighbors. However, most GNNs have shallow layers with a limited receptive field and may not achieve satisfactory performance especially when the number of labeled nodes is quite small. To address this challenge, we innovatively propose a graph few-shot learning (GFL) algorithm that incorporates prior knowledge learned from auxiliary graphs to improve classification accuracy on the target graph. Specifically, a transferable metric space characterized by a node embedding and a graph-specific prototype embedding function is shared between auxiliary graphs and the target, facilitating the transfer of structural knowledge. Extensive experiments and ablation studies on four real-world graph datasets demonstrate the effectiveness of our proposed model and the contribution of each component.more » « less
-
Edges in many real-world social/information networks are associated with rich text information (e.g., user-user communications or user-product reviews). However, mainstream network representation learning models focus on propagating and aggregating node attributes, lacking specific designs to utilize text semantics on edges. While there exist edge-aware graph neural networks, they directly initialize edge attributes as a feature vector, which cannot fully capture the contextualized text semantics of edges. In this paper, we propose Edgeformers, a framework built upon graph-enhanced Transformers, to perform edge and node representation learning by modeling texts on edges in a contextualized way. Specifically, in edge representation learning, we inject network information into each Transformer layer when encoding edge texts; in node representation learning, we aggregate edge representations through an attention mechanism within each node’s ego-graph. On five public datasets from three different domains, Edgeformers consistently outperform state-of-the-art baselines in edge classification and link prediction, demonstrating the efficacy in learning edge and node representations, respectively.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/HPEC62836.2024.10938526
