Towards Robust Graph Incremental Learning on Evolving Graphs
Incremental learning is a machine learning approach that involves training a model on a sequence of tasks, rather than all tasks at once. This ability to learn incrementally from a stream of tasks is crucial for many real-world applications. However, incremental learning is a challenging problem on graph-structured data, as many graph-related problems involve prediction tasks for each individual node, known as Node-wise Graph Incremental Learning (NGIL). This introduces non-independent and non-identically distributed characteristics in the sample data generation process, making it difficult to maintain the performance of the model as new tasks are added. In this paper, we focus on the inductive NGIL problem, which accounts for the evolution of graph structure (structural shift) induced by emerging tasks. We provide a formal formulation and analysis of the problem, and propose a novel regularization-based technique called Structural-Shift-Risk-Mitigation (SSRM) to mitigate the impact of the structural shift on catastrophic forgetting of the inductive NGIL problem. We show that the structural shift can lead to a shift in the input distribution for the existing tasks, and further lead to an increased risk of catastrophic forgetting. Through comprehensive empirical studies with several benchmark datasets, we demonstrate that our proposed method, Structural-Shift-Risk-Mitigation (SSRM), is flexible and easy to adapt to improve the performance of state-of-the-art GNN incremental learning frameworks in the inductive setting.
Code (0)
등록된 구현이 없습니다.
Tasks
Incremental LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Incremental Causal Graph Learning for Online Cyberattack Detection in Cyber-Physical Infrastructures
The escalating threat of cyberattacks on real-time critical infrastructures poses serious risks to public safety, demanding detection methods that effectively capture complex system interdependencies and adapt to evolvin…
Graph ClassificationAnomaly DetectionGraph LearningFILDNE: A Framework for Incremental Learning of Dynamic Networks Embeddings
Representation learning on graphs has emerged as a powerful mechanism to automate feature vector generation for downstream machine learning tasks. The advances in representation on graphs have centered on both homogeneou…
Dynamic graph embeddingGraph EmbeddingIncremental LearningLink Prediction+1IncNSA: Detecting communities incrementally from time-evolving networks based on node similarity
Many real-world systems can be abstracted as networks. As those systems always change dynamically in nature, the corresponding networks also evolve over time in general, and detecting communities from such time-evolving …
Community DetectionDynamic Community DetectionGraph ClusteringIncremental Learning with Concept Drift Detection and Prototype-based Embeddings for Graph Stream Classification
Data stream mining aims at extracting meaningful knowledge from continually evolving data streams, addressing the challenges posed by nonstationary environments, particularly, concept drift which refers to a change in th…
Decision MakingDrift DetectionIncremental LearningGOTHAM: Graph Class Incremental Learning Framework under Weak Supervision
Graphs are growing rapidly, along with the number of distinct label categories associated with them. Applications like e-commerce, healthcare, recommendation systems, and various social media platforms are rapidly moving…
Attributeclass-incremental learningClass Incremental LearningIncremental Learning+3