Leveraging Semantics for Incremental Learning in Multi-Relational Embeddings
arXiv:1905.12181
Abstract
Service robots benefit from encoding information in semantically meaningful ways to enable more robust task execution. Prior work has shown multi-relational embeddings can encode semantic knowledge graphs to promote generalizability and scalability, but only within a batched learning paradigm. We present Incremental Semantic Initialization (ISI), an incremental learning approach that enables novel semantic concepts to be initialized in the embedding in relation to previously learned embeddings of semantically similar concepts. We evaluate ISI on mined AI2Thor and MatterPort3D datasets; our experiments show that on average ISI improves immediate query performance by 41.4%. Additionally, ISI methods on average reduced the number of epochs required to approach model convergence by 78.2%.
arXiv comment10 pages, 6 figures, 3 tables
References in corpus (9)
- Distributed Representations of Words and Phrases and their Compositionality
- A Review of Relational Machine Learning for Knowledge Graphs
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Analogical Inference for Multi-Relational Embeddings
- Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
- Deep Generative Dual Memory Network for Continual Learning
- RoboBrain: Large-Scale Knowledge Engine for Robots
- Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach