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.
arXiv comment41 pages, 280 references
References in corpus (47)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Inductive Representation Learning on Large Graphs
- An Overview of Multi-Task Learning in Deep Neural Networks
- Understanding deep learning requires rethinking generalization
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Matching Networks for One Shot Learning
- ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
- Transductive Multi-view Zero-Shot Learning
- On First-Order Meta-Learning Algorithms
- Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
- Personalized Federated Learning: A Meta-Learning Approach
- Learning to Self-Train for Semi-Supervised Few-Shot Classification
- Few-shot classification in Named Entity Recognition Task
- Towards a Neural Statistician
- Learning Deep Representations of Fine-grained Visual Descriptions
- One-Shot Federated Learning
- Context-Dependent Fine-Grained Entity Type Tagging
- One-Shot Unsupervised Cross Domain Translation
- Deep Meta-Learning: Learning to Learn in the Concept Space
- Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
- Small Sample Learning in Big Data Era
- Few-shot Learning for Named Entity Recognition in Medical Text
- Improving One-Shot Learning through Fusing Side Information
- Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
- Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
- Meta-Graph: Few Shot Link Prediction via Meta Learning
- Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
- Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
- Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre)
- Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
- The effects of negative adaptation in Model-Agnostic Meta-Learning
- Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
- Zero-Shot Learning with Common Sense Knowledge Graphs
- A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Learning
- Meta Reasoning over Knowledge Graphs
- Fine-Grain Few-Shot Vision via Domain Knowledge as Hyperspherical Priors
- Few-Shot Generative Conversational Query Rewriting
- Few-Shot Knowledge Graph Completion
- Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
- Zero-Resource Cross-Domain Named Entity Recognition
- Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification
- Graph Few-shot Learning via Knowledge Transfer
- Out-of-Sample Representation Learning for Multi-Relational Graphs
- Knowledge Guided Metric Learning for Few-Shot Text Classification
- TransOMCS: From Linguistic Graphs to Commonsense Knowledge
- Deep Bidirectional Transformers for Relation Extraction without Supervision