相关论文: Mind the truncation gap: challenges of learning on…

Constructing states from sequences of observations is an important component of reinforcement learning agents. One solution for state construction is to use recurrent neural networks. Back-propagation through time (BPTT), and real-time…

Graph neural networks (GNN) suffer from severe inefficiency. It is mainly caused by the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization algorithms so that the…

With the process of urbanization and the rapid growth of population, the issue of traffic congestion has become an increasingly critical concern. Intelligent transportation systems heavily rely on real-time and precise prediction algorithms…

Dynamic interactions between entities are prevalent in domains like social platforms, financial systems, healthcare, and e-commerce. These interactions can be effectively represented as time-evolving graphs, where predicting future…

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…

Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has…

A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation. This makes BPTT…

Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to…

In recent years, there has been an increasing interest in the use of graph neural networks (GNNs) for analyzing dynamic graphs, which are graphs that evolve over time. However, there is still a lack of understanding of how different…

Graph neural networks (GNNs) have been broadly studied on dynamic graphs for their representation learning, majority of which focus on graphs with homogeneous structures in the spatial domain. However, many real-world graphs - i.e.,…

Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating…

Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of real-world graphs in domains like recommender systems, fraud detection, and molecular…

Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social…

In dynamic graphs, preserving temporal continuity is critical. However, Memory-based Dynamic Graph Neural Networks (MDGNNs) trained with large batches often disrupt event sequences, leading to temporal information loss. This discontinuity…

The current graph neural network (GNN) systems have established a clear trend of not showing training accuracy results, and directly or indirectly relying on smaller datasets for evaluations majorly. Our in-depth analysis shows that it…

Graph Neural Networks (GNNs) have superior capability in learning graph data. Full-graph GNN training generally has high accuracy, however, it suffers from large peak memory usage and encounters the Out-of-Memory problem when handling large…

Graph neural networks (GNNs) have achieved remarkable success across a wide range of applications, such as recommendation, drug discovery, and question answering. Behind the success of GNNs lies the backpropagation (BP) algorithm, which is…

Continual graph learning (CGL) aims to enable graph neural networks to incrementally learn from a stream of graph structured data without forgetting previously acquired knowledge. Existing methods particularly those based on experience…

Continual Graph Learning (CGL), which aims to accommodate new tasks over evolving graph data without forgetting prior knowledge, is garnering significant research interest. Mainstream solutions adopt the memory replay-based idea, ie,…

Predictive Coding (PC) is a biologically-inspired learning framework characterised by local, parallelisable operations, properties that enable energy-efficient implementation on neuromorphic hardware. Despite this, extending PC effectively…