Learning to Compare: Relation Network for Few-Shot Learning
We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning. Extensive experiments on five benchmarks demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.
Code (13)
Tasks
Few-Shot Image ClassificationFew-Shot LearningMeta-LearningRelationRelation NetworkZero-Shot LearningSimilar Papers 제목 키워드 기반
Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction
Few-shot relational learning for static knowledge graphs (KGs) has drawn greater interest in recent years, while few-shot learning for temporal knowledge graphs (TKGs) has hardly been studied. Compared to KGs, TKGs conta…
Few-Shot LearningKnowledge GraphsLink PredictionRelational ReasoningFewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
We present a Few-Shot Relation Classification Dataset (FewRel), consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. The relation of each sentence is first recognized by …
ClassificationFew-Shot LearningFew-Shot Relation ClassificationGeneral Classification+4Neural Snowball for Few-Shot Relation Learning
Knowledge graphs typically undergo open-ended growth of new relations. This cannot be well handled by relation extraction that focuses on pre-defined relations with sufficient training data. To address new relations with…
Knowledge GraphsRelationRelation ExtractionRelational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-…
Few-Shot LearningKnowledge Graph CompletionKnowledge GraphsMeta-Learning+1Revisiting Large Language Models as Zero-shot Relation Extractors
Relation extraction (RE) consistently involves a certain degree of labeled or unlabeled data even if under zero-shot setting. Recent studies have shown that large language models (LLMs) transfer well to new tasks out-of-…
Question AnsweringRelationRelation Extraction