Related papers: Overcoming Catastrophic Forgetting in Graph Neural…
Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems. However, GNNs on such applications are limited when there are…
Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification. In this work, we reveal the vulnerability of GNN to the imbalance of node labels. Traditional solutions for imbalanced…
Graph neural networks (GNNs) are widely applied in graph data modeling. However, existing GNNs are often trained in a task-driven manner that fails to fully capture the intrinsic nature of the graph structure, resulting in sub-optimal node…
Graph class-incremental learning (GCIL) allows graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge while retaining knowledge of old classes. Existing GCIL methods primarily…
Graph Neural Networks (GNNs) are a framework for graph representation learning, where a model learns to generate low dimensional node embeddings that encapsulate structural and feature-related information. GNNs are usually trained in an…
The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…
Temporal knowledge graph (TKG) completion models typically rely on having access to the entire graph during training. However, in real-world scenarios, TKG data is often received incrementally as events unfold, leading to a dynamic…
Continual learning (CL) is the research field that aims to build machine learning models that can accumulate knowledge continuously over different tasks without retraining from scratch. Previous studies have shown that pre-training graph…
Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. Despite recent remarkable progress in state-of-the-art deep learning, deep…
Many real-world graph learning tasks require handling dynamic graphs where new nodes and edges emerge. Dynamic graph learning methods commonly suffer from the catastrophic forgetting problem, where knowledge learned for previous graphs is…
Graph processes exhibit a temporal structure determined by the sequence index and and a spatial structure determined by the graph support. To learn from graph processes, an information processing architecture must then be able to exploit…
Recently, graph neural networks (GNNs) have proved to be suitable in tasks on unstructured data. Particularly in tasks as community detection, node classification, and link prediction. However, most GNN models still operate with static…
Lifelong learning aims to develop machine learning systems that can learn new tasks while preserving the performance on previous learned tasks. In this paper we present a method to overcome catastrophic forgetting on convolutional neural…
In the last decade or so, we have witnessed deep learning reinvigorating the machine learning field. It has solved many problems in the domains of computer vision, speech recognition, natural language processing, and various other tasks…
In this paper, we propose Graph Retention Networks (GRNs) as a unified architecture for deep learning on dynamic graphs. The GRN extends the concept of retention into dynamic graph data as graph retention, equipping the model with three key…
Lifelong learning is challenging for deep neural networks due to their susceptibility to catastrophic forgetting. Catastrophic forgetting occurs when a trained network is not able to maintain its ability to accomplish previously learned…
How to properly model graphs is a long-existing and important problem in NLP area, where several popular types of graphs are knowledge graphs, semantic graphs and dependency graphs. Comparing with other data structures, such as sequences…
Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In…
Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible…
Continual learning models allow to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios in which the models are trained using different data with various distributions, neural networks…