Graph neural networks (GNNs) are a type of deep learning models that are trained on graphs and have been successfully applied in various domains. Despite the effectiveness of GNNs, it is still challenging for GNNs to efficiently scale to large graphs. As a remedy, distributed computing becomes a promising solution of training large-scale GNNs, since it is able to provide abundant computing resources. However, the dependency of graph structure increases the difficulty of achieving high-efficiency distributed GNN training, which suffers from the massive communication and workload imbalance. In recent years, many efforts have been made on distributed GNN training, and an array of training algorithms and systems have been proposed. Yet, there is a lack of systematic review of the optimization techniques for the distributed execution of GNN training. In this survey, we analyze three major challenges in distributed GNN training: massive feature communication, the loss of model accuracy, and workload imbalance. Then, we introduce a new taxonomy for the optimization techniques in distributed GNN training that address the above challenges. The new taxonomy classifies existing techniques into four categories: GNN data partition, GNN batch generation, GNN execution model, and GNN communication protocol. We carefully discuss the techniques in each category. In the conclusion, we summarize existing distributed GNN systems for multi–graphics processing units (GPUs), GPU-clusters and central processing unit (CPU)-clusters, respectively, and present a discussion about the future direction of distributed GNN training.

Graph Neural Networks (GNNs) have been a prevailing technique for tackling various analysis tasks on graph data. A key premise for the remarkable performance of GNNs relies on complete and trustworthy initial graph descriptions (i.e., node features and graph structure), which is often not satisfied since real-world graphs are often incomplete due to various unavoidable factors. In particular, GNNs face greater challenges when both node features and graph structure are incomplete at the same time. The existing methods either focus on feature completion or structure completion. They usually rely on the matching relationship between features and structure, or employ joint learning of node representation and feature (or structure) completion in the hope of achieving mutual benefit. However, recent studies confirm that the mutual interference between features and structure leads to the degradation of GNN performance. When both features and structure are incomplete, the mismatch between features and structure caused by the missing randomness exacerbates the interference between the two, which may trigger incorrect completions that negatively affect node representation. To this end, in this paper we propose a general GNN framework based on teacher-student distillation to improve the performance of GNNs on incomplete graphs, namely T2-GNN. To avoid the interference between features and structure, we separately design feature-level and structure-level teacher models to provide targeted guidance for student model (base GNNs, such as GCN) through distillation. Then we design two personalized methods to obtain well-trained feature and structure teachers. To ensure that the knowledge of the teacher model is comprehensively and effectively distilled to the student model, we further propose a dual distillation mode to enable the student to acquire as much expert knowledge as possible. Extensive experiments on eight benchmark datasets demonstrate the effectiveness and robustness of the new framework on graphs with incomplete features and structure.

Traffic prediction is an important component of the intelligent transportation system. Existing deep learning methods encode temporal information and spatial information separately or iteratively. However, the spatial and temporal information is highly correlated in a traffic network, so existing methods may not learn the complex spatial-temporal dependencies hidden in the traffic network due to the decomposed model design. To overcome this limitation, we propose a new model named Trafformer, which unifies spatial and temporal information in one transformer-style model. Trafformer enables every node at every timestamp interact with every other node in every other timestamp in just one step in the spatial-temporal correlation matrix. This design enables Trafformer to catch complex spatial-temporal dependencies. Following the same design principle, we use the generative style decoder to predict multiple timestamps in only one forward operation instead of the iterative style decoder in Transformer. Furthermore, to reduce the complexity brought about by the huge spatial-temporal self-attention matrix, we also propose two variants of Trafformer to further improve the training and inference speed without losing much effectivity. Extensive experiments on two traffic datasets demonstrate that Trafformer outperforms existing methods and provides a promising future direction for the spatial-temporal traffic prediction problem.

In order to mine latent semantics from text data, word embedding and topic modeling are two major methodologies in industry. From a pragmatic perspective, each of these two lines of semantic models faces increasing challenges from real-life applications. However, modern text mining tasks typically require a panoramic view of the latent semantics. Hence, discovering heterogeneous semantics (e.g., heterogeneous types of latent topics) is critical for the performance of these tasks, and it is necessary to design a model that meets this demand. Furthermore, with the arrival of the big data era and the increasing awareness of data privacy, it is necessary to study the issues of mining heterogeneous semantics with high efficiency while avoiding compromising data privacy. In this work, we develop a novel method called Heterogeneous Latent Topic Discovery (HLTD) which seamlessly integrates topic modeling with word embedding to discover heterogeneous latent topics. By coupling parameter-server architecture with new private sampling algorithms, HLTD can be efficiently trained with effective protection of underlying data privacy. We evaluate HLTD through a wide range of qualitative and quantitative metrics in industry. Extensive experiments demonstrates the superiority of HLTD over the state-of-the-arts.

Multimodal path queries over transportation networks are receiving increasing attention due to their widespread applications. A multimodal path query consists of finding multimodal journeys from source to destination in transportation networks, including unrestricted walking, driving, cycling, and schedule-based public transportation. Transportation networks are generally continent-sized. This characteristic highlights the need for parallel computing to accelerate multimodal path queries. Meanwhile, transportation networks are often fragmented and distributively stored on different machines. This situation calls for exploiting parallel computing power for these distributed systems. Therefore, in this paper, we study distributed multimodal path (DMP) queries over large transportation networks. We develop algorithms to explore parallel computation. When evaluating a DMP query Q on a distributed multimodal graph Gmult, we show that the algorithms possess the following performance guarantees, irrespective of how Gmult is fragmented and distributed: (1) each machine is visited only once; (2) the total network traffic is determined by the size of Q and the fragmentation of Gmult, independent of the size of Gmult; (3) the response time is decided by the largest fragment of Gmult; and (4) the algorithm is parallel scalable. Using real-life and synthetic data, we experimentally verify that the algorithms are scalable on large graphs.