Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
Pengda Qin, Xin Wang, Wenhu Chen, Chunyun Zhang, Weiran Xu, William Yang Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | NELL-ZS zero-shot link prediction · NELL-ZS | MRR: 0.235 -> 0.253 | Improved |
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | NELL-ZS zero-shot link prediction · NELL-ZS | Hits@10: 32.6 -> 37.1 | Improved |
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | NELL-ZS zero-shot link prediction · NELL-ZS | Hits@5: 28.4 -> 30.5 | Improved |
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | NELL-ZS zero-shot link prediction · NELL-ZS | Hits@1: 18.5 -> 19.4 | Improved |
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | Wiki-ZS zero-shot link prediction · Wiki-ZS | MRR: 0.189 -> 0.208 | Improved |
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | Wiki-ZS zero-shot link prediction · Wiki-ZS | Hits@10: 23.6 -> 29.4 | Improved |
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | Wiki-ZS zero-shot link prediction · Wiki-ZS | Hits@5: 21.0 -> 24.1 | Improved |
| Use ZSGAN_KG with DistMult rather than ZS-DistMult | Wiki-ZS zero-shot link prediction · Wiki-ZS | Hits@1: 16.1 -> 16.5 | Improved |
| Use Word2Vec rather than BERT word representations (ablation) | ZSGAN_KG with DistMult · NELL-ZS | MRR: 0.237 -> 0.253 | Improved |
| Use Word2Vec rather than BERT word representations (ablation) | ZSGAN_KG with DistMult · Wiki-ZS | MRR: 0.175 -> 0.208 | Improved |
| Replace the bag-of-words text input with a CNN or LSTM text encoder (ablation) | ZSGAN_KG · Zero-shot relational learning | link prediction performance | Hurt |
Closest papers by meaning
- Incorporating GAN for Negative Sampling in Knowledge Representation Learning (AAAI 2018 · similarity 0.88)
- Rethinking Knowledge Graph Propagation for Zero-Shot Learning (CVPR 2019 · similarity 0.88)
- A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts (CVPR 2018 · similarity 0.88)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.85)
- LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings (NeurIPS 2024 · similarity 0.85)
- Towards Foundation Models for Knowledge Graph Reasoning (ICLR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
