Disentangle-based Continual Graph Representation Learning

2020-10-06 · EMNLP 2020 11 · Xiaoyu Kou, Yankai Lin, Shaobo Liu, Peng Li, Jie zhou, Yan Zhang

Graph embedding (GE) methods embed nodes (and/or edges) in graph into a low-dimensional semantic space, and have shown its effectiveness in modeling multi-relational data. However, existing GE models are not practical in real-world applications since it overlooked the streaming nature of incoming data. To address this issue, we study the problem of continual graph representation learning which aims to continually train a GE model on new data to learn incessantly emerging multi-relational data while avoiding catastrophically forgetting old learned knowledge. Moreover, we propose a disentangle-based continual graph representation learning (DiCGRL) framework inspired by the human's ability to learn procedural knowledge. The experimental results show that DiCGRL could effectively alleviate the catastrophic forgetting problem and outperform state-of-the-art continual learning models.

📄 PDF Abstract BibTeX arXiv:2010.02565

Code (1)

KXY-PUBLIC/DiCGRL pytorch

Tasks

Continual Learning Graph Embedding Graph Representation Learning Representation Learning

Disentanglement of Color and Shape Representations for Continual Learning

2020-07-13 · David Berga, Marc Masana, Joost Van de Weijer

We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested …

Continual Learning Disentanglement

Continual Learning for Text Classification with Information Disentanglement Based Regularization

2021-04-12 · NAACL 2021 4 · Yufan Huang, Yanzhe Zhang, Jiaao Chen, Xuezhi Wang 외

Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous …

Continual Learning Disentanglement General Classification Sentence+2

Active perception and disentangled representations allow continual, episodic zero and few-shot learning

2026-02-22 · David Rawlinson, Gideon Kowadlo arxiv

Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system needs to generalize. Training models for generalization typically produces entangled…

Continual Learning Few-Shot Learning

GraphSAD: Learning Graph Representations with Structure-Attribute Disentanglement

2021-01-01 · Minghao Xu, Hang Wang, Bingbing Ni, Wenjun Zhang 외

Graph Neural Networks (GNNs) learn effective node/graph representations by aggregating the attributes of neighboring nodes, which commonly derives a single representation mixing the information of graph structure and nod…

Attribute Disentanglement Graph Classification

Learning Network Representations with Disentangled Graph Auto-Encoder

2024-02-02 · Di Fan, Chuanhou Gao

The (variational) graph auto-encoder is widely used to learn representations for graph-structured data. However, the formation of real-world graphs is a complicated and heterogeneous process influenced by latent factors.…

Decoder Learning Network Representations