相关论文: GraphKeeper: Graph Domain-Incremental Learning via…

Graphs are versatile tools for representing structured data. As a result, a variety of machine learning methods have been studied for graph data analysis. Although many such learning methods depend on the measurement of differences between…

Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual…

Continual learning (CL) with Vision-Language Models (VLMs) has overcome the constraints of traditional CL, which only focuses on previously encountered classes. During the CL of VLMs, we need not only to prevent the catastrophic forgetting…

Domain shift is a fundamental problem in visual recognition which typically arises when the source and target data follow different distributions. The existing domain adaptation approaches which tackle this problem work in the closed-set…

Nowadays, real-world data, including graph-structure data, often arrives in a streaming manner, which means that learning systems need to continuously acquire new knowledge without forgetting previously learned information. Although…

Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient…

Recent advances in graph machine learning have shifted to data-centric paradigms, driven by two emerging fields: (1) Federated graph learning (FGL) enables multi-client collaboration but faces challenges from data and task heterogeneity,…

Knowledge graph (KG) embedding encodes the entities and relations from a KG into low-dimensional vector spaces to support various applications such as KG completion, question answering, and recommender systems. In real world, knowledge…

This paper proposes two novel knowledge transfer techniques for class-incremental learning (CIL). First, we propose data-free generative replay (DF-GR) to mitigate catastrophic forgetting in CIL by using synthetic samples from a generative…

Inductive link prediction (ILP) is to predict links for unseen entities in emerging knowledge graphs (KGs), considering the evolving nature of KGs. A more challenging scenario is that emerging KGs consist of only unseen entities, called as…

Graph out-of-distribution (OOD) generalization remains a major challenge in graph learning since graph neural networks (GNNs) often suffer from severe performance degradation under distribution shifts. Invariant learning, aiming to extract…

With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting…

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be…

The quality of graph-structured data is fundamental to the success of modern graph analysis techniques such as Graph Neural Networks (GNNs). However, real-world graph data is often suboptimal, suffering from issues such as noise and…

Continual graph learning (CGL) studies the problem of learning from an infinite stream of graph data, consolidating historical knowledge, and generalizing it to the future task. At once, only current graph data are available. Although some…

Graph representation learning has emerged as a powerful tool for preserving graph topology when mapping nodes to vector representations, enabling various downstream tasks such as node classification and community detection. However, most…

Knowledge graph (KG) embedding seeks to learn vector representations for entities and relations. Conventional models reason over graph structures, but they suffer from the issues of graph incompleteness and long-tail entities. Recent…

Deep multi-task learning attracts much attention in recent years as it achieves good performance in many applications. Feature learning is important to deep multi-task learning for sharing common information among tasks. In this paper, we…

Learning effective embedding has been proved to be useful in many real-world problems, such as recommender systems, search ranking and online advertisement. However, one of the challenges is data sparsity in learning large-scale item…

Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning. Recent works focused on designing self-supervised pre-training tasks to extract useful…