No abstract

Temporal domain generalization is a promising yet extremely challenging area where the goal is to learn models under temporally changing data distributions and generalize to unseen data distributions following the trends of the change. The advancement of this area is challenged by: 1) characterizing data distribution drift and its impacts on models, 2) expressiveness in tracking the model dynamics, and 3) theoretical guarantee on the performance. To address them, we propose a Temporal Domain Generalization with Drift-Aware Dynamic Neural Network (DRAIN) framework. Specifically, we formulate the problem into a Bayesian framework that jointly models the relation between data and model dynamics. We then build a recurrent graph generation scenario to characterize the dynamic graph-structured neural networks learned across different time points. It captures the temporal drift of model parameters and data distributions and can predict models in the future without the presence of future data. In addition, we explore theoretical guarantees of the model performance under the challenging temporal DG setting and provide theoretical analysis, including uncertainty and generalization error. Finally, extensive experiments on several real-world benchmarks with temporal drift demonstrate the proposed method's effectiveness and efficiency.

Despite the recent success of Graph Neural Networks (GNNs), it remains challenging to train a GNN on large graphs (e.g., with over millions of nodes & billions of edges), which are prevalent in various graph-based applications such as social networks, recommender systems, and knowledge graphs. Traditional sampling-based methods accelerate GNN by dropping edges and nodes, which impairs the graph integrity and model performance. Differently, distributed GNN algorithms, which accelerate GNN training by utilizing multiple computing devices, can be classified into two types: "partition-based" methods enjoy low communication cost but suffer from information loss due to dropped edges, while "propagation-based" methods avoid information loss but suffer prohibitive communication overhead caused by neighbor explosion. To jointly address these problems, this paper proposes DIstributed Graph Embedding SynchronizaTion (DIGEST), a novel distributed GNN training framework that synergizes the complementary strength of both categories of existing methods. During subgraph parallel training, we propose to let each device store the historical embedding of its neighbors in other subgraphs. Therefore, our method does not discard any neighbors in other subgraphs (which leads to information loss), nor does it updates them intensively (which leads to communication cost). This effectively avoids (1) the intensive computation on explosively-increasing neighbors and (2) excessive communications across different devices. We proved that the approximation error induced by the staleness of historical embedding can be upper bounded and it does NOT affect the GNN model's expressiveness. More importantly, our convergence analysis demonstrates that DIGEST enjoys the state-of-the-art convergence rate. Extensive experimental evaluation on large, real-world graph datasets shows that DIGEST achieves up to 21.82× speedup without compromising the performance compared to state-of-the-art distributed GNN training frameworks.

Multi-task learning is a framework that enforces different learning tasks to share their knowledge to improve their generalization performance. It is a hot and active domain that strives to handle several core issues; particularly, which tasks are correlated and similar, and how to share the knowledge among correlated tasks. Existing works usually do not distinguish the polarity and magnitude of feature weights and commonly rely on linear correlation, due to three major technical challenges in: 1) optimizing the models that regularize feature weight polarity, 2) deciding whether to regularize sign or magnitude, 3) identifying which tasks should share their sign and/or magnitude patterns. To address them, this paper proposes a new multi-task learning framework that can regularize feature weight signs across tasks. We innovatively formulate it as a biconvex inequality constrained optimization with slacks and propose a new efficient algorithm for the optimization with theoretical guarantees on generalization performance and convergence. Extensive experiments on multiple datasets demonstrate the proposed methods' effectiveness, efficiency, and reasonableness of the regularized feature weighted patterns.

No abstract