mlsanityData to 14 Oct 2026

Meta-Semantics Augmented Few-Shot Relational Learning

arXiv 2505.05684 ↗First posted 8 May 2025cs.AI cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Few-shot relational learning on knowledge graph (KGs) aims to perform reasoning over relations with only a few training examples. While current methods have focused primarily on leveraging specific relational information, rich semantics inherent in KGs have been largely overlooked. To bridge this gap, we propose PromptMeta, a novel prompted meta-learning framework that seamlessly integrates meta-semantics with relational information for few-shot relational learning. PromptMeta introduces two core innovations: (1) a Meta-Semantic Prompt (MSP) pool that learns and consolidates high-level meta-semantics shared across tasks, enabling effective knowledge transfer and adaptation to newly emerging relations; and (2) a learnable fusion mechanism that dynamically combines meta-semantics with task-specific relational information tailored to different few-shot tasks. Both components are optimized jointly with model parameters within a meta-learning framework. Extensive experiments and analyses on two real-world KG benchmarks validate the effectiveness of PromptMeta in adapting to new relations with limited supervision.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 8 May 2025.

Builds on

18 of 39 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  4. 2016Complex Embeddings for Simple Link Predictioncited by 902
  5. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  6. 2019Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systemscited by 107
  7. 2018One-Shot Relational Learning for Knowledge Graphscited by 78
  8. 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
  9. 2019Few-Shot Knowledge Graph Completioncited by 63
  10. 2023HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learningcited by 45
  11. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  12. 2020Adaptive Attentional Network for Few-Shot Knowledge Graph Completioncited by 42
6 more
  1. 2021Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completioncited by 32
  2. 2023Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphscited by 23
  3. 2023Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphscited by 23
  4. 2020CoCoLM: COmplex COmmonsense Enhanced Language Model with Discourse Relationscited by 15
  5. 2024Few-shot Knowledge Graph Relational Reasoning via Subgraph Adaptationcited by 3
  6. 2024Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphscited by 3

Built on by

Not cited yet.