What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
arXiv:2106.06410
Abstract
Supervised machine learning has several drawbacks that make it difficult to use in many situations. Drawbacks include: heavy reliance on massive training data, limited generalizability and poor expressiveness of high-level semantics. Low-shot Learning attempts to address these drawbacks. Low-shot learning allows the model to obtain good predictive power with very little or no training data, where structured knowledge plays a key role as a high-level semantic representation of human. This article will review the fundamental factors of low-shot learning technologies, with a focus on the operation of structured knowledge under different low-shot conditions. We also introduce other techniques relevant to low-shot learning. Finally, we point out the limitations of low-shot learning, the prospects and gaps of industrial applications, and future research directions.
41 pages, 280 references
References in corpus (17)
- An Overview of Multi-Task Learning in Deep Neural Networks
- Understanding deep learning requires rethinking generalization
- Transductive Multi-view Zero-Shot Learning
- Few-shot classification in Named Entity Recognition Task
- One-Shot Federated Learning
- Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
- Improving One-Shot Learning through Fusing Side Information
- Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
- Meta-Graph: Few Shot Link Prediction via Meta Learning
- Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
- Fine-Grain Few-Shot Vision via Domain Knowledge as Hyperspherical Priors
- Few-Shot Generative Conversational Query Rewriting
- Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
- Few-Shot Knowledge Graph Completion
- Knowledge Guided Metric Learning for Few-Shot Text Classification
- TransOMCS: From Linguistic Graphs to Commonsense Knowledge
- Deep Bidirectional Transformers for Relation Extraction without Supervision