mlsanityData to 7 Oct 2026

Benchmarking Knowledge-driven Zero-shot Learning

arXiv 2106.15047 ↗First posted 29 Jun 2021cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

External knowledge (a.k.a. side information) plays a critical role in zero-shot learning (ZSL) which aims to predict with unseen classes that have never appeared in training data. Several kinds of external knowledge, such as text and attribute, have been widely investigated, but they alone are limited with incomplete semantics. Some very recent studies thus propose to use Knowledge Graph (KG) due to its high expressivity and compatibility for representing kinds of knowledge. However, the ZSL community is still in short of standard benchmarks for studying and comparing different external knowledge settings and different KG-based ZSL methods. In this paper, we proposed six resources covering three tasks, i.e., zero-shot image classification (ZS-IMGC), zero-shot relation extraction (ZS-RE), and zero-shot KG completion (ZS-KGC). Each resource has a normal ZSL benchmark and a KG containing semantics ranging from text to attribute, from relational knowledge to logical expressions. We have clearly presented these resources including their construction, statistics, data formats and usage cases w.r.t. different ZSL methods. More importantly, we have conducted a comprehensive benchmarking study, with two general and state-of-the-art methods, two setting-specific methods and one interpretable method. We discussed and compared different ZSL paradigms w.r.t. different external knowledge settings, and found that our resources have great potential for developing more advanced ZSL methods and more solutions for applying KGs for augmenting machine learning. All the resources are available at https://github.com/China-UK-ZSL/Resources_for_KZSL.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 78 references that are in the map. First posted on arXiv 29 Jun 2021.

Builds on

38 of 78 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  5. 2016Variational Graph Auto-Encoderscited by 1,373
  6. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  7. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  8. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  9. 2017Zero-Shot Relation Extraction via Reading Comprehensioncited by 425
  10. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  11. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 323
  12. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
26 more
  1. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  2. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  3. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  4. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  5. 2019Zero-Shot Entity Linking by Reading Entity Descriptionscited by 124
  6. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  7. 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
  8. 2018Rethinking Knowledge Graph Propagation for Zero-Shot Learningcited by 87
  9. 2020Knowledge Graph Embedding for Link Prediction: A Comparative Analysiscited by 85
  10. 2017Multi-Label Zero-Shot Learning with Structured Knowledge Graphscited by 72
  11. 2021Argumentative XAI: A Surveycited by 66
  12. 2019Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoningcited by 63
  13. 2020OWL2Vec*: Embedding of OWL Ontologiescited by 63
  14. 2021ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learningcited by 46
  15. 2021OntoZSL: Ontology-enhanced Zero-shot Learningcited by 45
  16. 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
  17. 2021Knowledge-aware Zero-Shot Learning: Survey and Perspectivecited by 41
  18. 2019A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly?cited by 31
  19. 2020Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphscited by 30
  20. 2020ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpagescited by 30
  21. 2019Integrating Semantic Knowledge to Tackle Zero-shot Text Classificationcited by 28
  22. 2020Logic-guided Semantic Representation Learning for Zero-Shot Relation Classificationcited by 18
  23. 2020Zero-Shot Learning with Common Sense Knowledge Graphscited by 17
  24. 2019An Open-World Extension to Knowledge Graph Completion Modelscited by 16
  25. 2018Knowledge-based Transfer Learning Explanationcited by 12
  26. 2020Improving Zero Shot Learning Baselines with Commonsense Knowledgecited by 10

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 1; 2024: 1.

6 papers.

  1. 2022Relational Message Passing for Fully Inductive Knowledge Graph Completioncited by 29
  2. 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23
  3. 2023UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Trainingcited by 14
  4. 2022Segmenting Known Objects and Unseen Unknowns without Prior Knowledgecited by 9
  5. 2022Disentangled Ontology Embedding for Zero-shot Learningcited by 8
  6. 2024Description Boosting for Zero-Shot Entity and Relation Classificationcited by 0