# Rethinking Knowledge Graph Propagation for Zero-Shot Learning

arXiv: https://arxiv.org/abs/1805.11724 · HTML: https://mlsanity.com/paper/1805.11724/

## Key facts

- Cited by 87 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2018.

## Built on by (most cited first, 30 of 87)

- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [Learning Graph Embeddings for Compositional Zero-shot Learning](https://mlsanity.com/paper/2102.01987/) (2021)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future](https://mlsanity.com/paper/2105.13137/) (2021)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [Learning Graph Embeddings for Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2105.01017/) (2021)
- [Introducing Language Guidance in Prompt-based Continual Learning](https://mlsanity.com/paper/2308.15827/) (2023)
- [OntoZSL: Ontology-enhanced Zero-shot Learning](https://mlsanity.com/paper/2102.07339/) (2021)
- [Knowledge-aware Zero-Shot Learning: Survey and Perspective](https://mlsanity.com/paper/2103.00070/) (2021)
- [SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2108.12517/) (2021)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation](https://mlsanity.com/paper/2112.09445/) (2021)
- [Learning Domain Invariant Prompt for Vision-Language Models](https://mlsanity.com/paper/2212.04196/) (2022)
- [Contrastive Language-Image Pre-Training with Knowledge Graphs](https://mlsanity.com/paper/2210.08901/) (2022)
- [DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning](https://mlsanity.com/paper/2207.01328/) (2022)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2203.10444/) (2022)
- [I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification](https://mlsanity.com/paper/2209.10304/) (2022)
- [End-to-End Active Speaker Detection](https://mlsanity.com/paper/2203.14250/) (2022)
- [Cycle Representation Learning for Inductive Relation Prediction](https://mlsanity.com/paper/2110.02510/) (2021)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation](https://mlsanity.com/paper/2104.08945/) (2021)
- [Directed Graph Auto-Encoders](https://mlsanity.com/paper/2202.12449/) (2022)
- [Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification](https://mlsanity.com/paper/2203.01386/) (2022)
- [Large Language Models are Good Prompt Learners for Low-Shot Image Classification](https://mlsanity.com/paper/2312.04076/) (2023)
- [FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations](https://mlsanity.com/paper/2203.16639/) (2022)
- [Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning](https://mlsanity.com/paper/2409.17270/) (2024)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [Neuromorphic Camera Denoising using Graph Neural Network-driven Transformers](https://mlsanity.com/paper/2112.09685/) (2021)

## Abstract (arXiv)

Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, multi-layer architectures, which are required to propagate knowledge to distant nodes in the graph, dilute the knowledge by performing extensive Laplacian smoothing at each layer and thereby consequently decrease performance. In order to still enjoy the benefit brought by the graph structure while preventing dilution of knowledge from distant nodes, we propose a Dense Graph Propagation (DGP) module with carefully designed direct links among distant nodes. DGP allows us to exploit the hierarchical graph structure of the knowledge graph through additional connections. These connections are added based on a node's relationship to its ancestors and descendants. A weighting scheme is further used to weigh their contribution depending on the distance to the node to improve information propagation in the graph. Combined with finetuning of the representations in a two-stage training approach our method outperforms state-of-the-art zero-shot learning approaches.