More Like this

1. Learning Graph Neural Networks with Positive and Unlabeled Nodes

   https://doi.org/10.1145/3450316  

   Wu, Man; Pan, Shirui; Du, Lan; Zhu, Xingquan (June 2021, ACM Transactions on Knowledge Discovery from Data)

   null (Ed.)

   Graph neural networks (GNNs) are important tools for transductive learning tasks, such as node classification in graphs, due to their expressive power in capturing complex interdependency between nodes. To enable GNN learning, existing works typically assume that labeled nodes, from two or multiple classes, are provided, so that a discriminative classifier can be learned from the labeled data. In reality, this assumption might be too restrictive for applications, as users may only provide labels of interest in a single class for a small number of nodes. In addition, most GNN models only aggregate information from short distances ( e.g. , 1-hop neighbors) in each round, and fail to capture long-distance relationship in graphs. In this article, we propose a novel GNN framework, long-short distance aggregation networks, to overcome these limitations. By generating multiple graphs at different distance levels, based on the adjacency matrix, we develop a long-short distance attention model to model these graphs. The direct neighbors are captured via a short-distance attention mechanism, and neighbors with long distance are captured by a long-distance attention mechanism. Two novel risk estimators are further employed to aggregate long-short-distance networks, for PU learning and the loss is back-propagated for model learning. Experimental results on real-world datasets demonstrate the effectiveness of our algorithm. 

   more » « less
2. TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs

   Wang, Yuke; Feng, Boyuan; Wang, Zheng; Huang, Guyue; Ding, Yufei. (July 2023, USENIX Association)

   Recently, graph neural networks (GNNs), as the backbone of graph-based machine learning, demonstrate great success in various domains (e.g., e-commerce). However, the performance of GNNs is usually unsatisfactory due to the highly sparse and irregular graph-based operations. To this end, we propose TC-GNN, the first GNN acceleration framework based on GPU Tensor Core Units (TCUs). The core idea is to reconcile the "Sparse" GNN computation with the high-performance "Dense" TCUs. Specifically, we conduct an in-depth analysis of the sparse operations in mainstream GNN computing frameworks. We introduce a novel sparse graph translation technique to facilitate TCU processing of the sparse GNN workload. We implement an effective CUDA core and TCU collaboration design to fully utilize GPU resources. We integrate MGG with the PyTorch framework for high programmability. Rigorous experiments show an average of 1.70× speedup over the state-of-the-art DGL framework across various models and datasets. 

   more » « less
3. Don’t Just Prune by Magnitude! Your Mask Topology is Another Secret Weapon

   Hoang, Duc; Kundu, Souvik; Liu, Shiwei; Wang, Zhangyang (December 2023, Advances in neural information processing systems)

   Recent years have witnessed significant progress in understanding the relationship between the connectivity of a deep network's architecture as a graph, and the network's performance. A few prior arts connected deep architectures to expander graphs or Ramanujan graphs, and particularly,[7] demonstrated the use of such graph connectivity measures with ranking and relative performance of various obtained sparse sub-networks (i.e. models with prune masks) without the need for training. However, no prior work explicitly explores the role of parameters in the graph's connectivity, making the graph-based understanding of prune masks and the magnitude/gradient-based pruning practice isolated from one another. This paper strives to fill in this gap, by analyzing the Weighted Spectral Gap of Ramanujan structures in sparse neural networks and investigates its correlation with final performance. We specifically examine the evolution of sparse structures under a popular dynamic sparse-to-sparse network training scheme, and intriguingly find that the generated random topologies inherently maximize Ramanujan graphs. We also identify a strong correlation between masks, performance, and the weighted spectral gap. Leveraging this observation, we propose to construct a new "full-spectrum coordinate'' aiming to comprehensively characterize a sparse neural network's promise. Concretely, it consists of the classical Ramanujan's gap (structure), our proposed weighted spectral gap (parameters), and the constituent nested regular graphs within. In this new coordinate system, a sparse subnetwork's L2-distance from its original initialization is found to have nearly linear correlated with its performance. Eventually, we apply this unified perspective to develop a new actionable pruning method, by sampling sparse masks to maximize the L2-coordinate distance. Our method can be augmented with the "pruning at initialization" (PaI) method, and significantly outperforms existing PaI methods. With only a few iterations of training (e.g 500 iterations), we can get LTH-comparable performance as that yielded via "pruning after training", significantly saving pre-training costs. Codes can be found at: https://github.com/VITA-Group/FullSpectrum-PAI. 

   more » « less
4. {MGG}: Accelerating Graph Neural Networks with {Fine-Grained} {Intra-Kernel} {Communication-Computation} Pipelining on {Multi-GPU} Platforms

   Wang, Yuke; Feng, Boyuan; Wang, Zheng; Barker, Kevin; Li, Ang; Ding, Yufei. (July 2023, USENIX Association)

   The increasing size of input graphs for graph neural networks (GNNs) highlights the demand for using multi-GPU platforms. However, existing multi-GPU GNN systems optimize the computation and communication individually based on the conventional practice of scaling dense DNNs. For irregularly sparse and fine-grained GNN workloads, such solutions miss the opportunity to jointly schedule/optimize the computation and communication operations for high-performance delivery. To this end, we propose MGG , a novel system design to accelerate full-graph GNNs on multi-GPU platforms. The core of MGG is its novel dynamic software pipeline to facilitate fine-grained computation-communication overlapping within a GPU kernel. Specifically, MGG introduces GNN-tailored pipeline construction and GPU-aware pipeline mapping to facilitate workload balancing and operation overlapping. MGG also incorporates an intelligent runtime design with analytical modeling and optimization heuristics to dynamically improve the execution performance. Extensive evaluation reveals that MGG outperforms state-of-the-art full-graph GNN systems across various settings: on average 4.41×, 4.81×, and 10.83× faster than DGL, MGG-UVM, and ROC, respectively. 

   more » « less
5. Mean‐field limit of non‐exchangeable systems

   https://doi.org/10.1002/cpa.22235  

   Jabin, Pierre‐Emmanuel; Poyato, David; Soler, Juan (November 2024, Communications on Pure and Applied Mathematics)

   Abstract This paper deals with the derivation of the mean‐field limit for multi‐agent systems on a large class of sparse graphs. More specifically, the case of non‐exchangeable multi‐agent systems consisting of non‐identical agents is addressed. The analysis does not only involve PDEs and stochastic analysis but also graph theory through a new concept of limits of sparse graphs (extended graphons) that reflect the structure of the connectivities in the network and has critical effects on the collective dynamics. In this article some of the main restrictive hypothesis in the previous literature on the connectivities between the agents (dense graphs) and the cooperation between them (symmetric interactions) are removed. 

   more » « less