# ATGNN: Audio Tagging Graph Neural Network

arXiv: https://arxiv.org/abs/2311.01526 · HTML: https://mlsanity.com/paper/2311.01526/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 26 references that are in the map.
- First posted on arXiv 2 Nov 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [Audio Transformers](https://mlsanity.com/paper/2105.00335/) (2021)
- [Speaker diarization with session-level speaker embedding refinement using graph neural networks](https://mlsanity.com/paper/2005.11371/) (2020)
- [Multi-scale speaker embedding-based graph attention networks for speaker diarisation](https://mlsanity.com/paper/2110.03361/) (2021)
- [An Ontology-Aware Framework for Audio Event Classification](https://mlsanity.com/paper/2001.10048/) (2020)

## Built on by (most cited first, 4 of 4)

- [Refining music sample identification with a self-supervised graph neural network](https://mlsanity.com/paper/2506.14684/) (2025)
- [LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging](https://mlsanity.com/paper/2501.03464/) (2025)
- [MAGIC-Enhanced Keyword Prompting for Zero-Shot Audio Captioning with CLIP Models](https://mlsanity.com/paper/2509.12591/) (2025)
- [Graph in Graph Neural Network](https://mlsanity.com/paper/2407.00696/) (2024)

## Abstract (arXiv)

Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging. Recent works have shown that despite stacking multiple layers, the receptive field of CNNs remains severely limited. Transformers on the other hand are able to map global context through self-attention, but treat the spectrogram as a sequence of patches which is not flexible enough to capture irregular audio objects. In this work, we treat the spectrogram in a more flexible way by considering it as graph structure and process it with a novel graph neural architecture called ATGNN. ATGNN not only combines the capability of CNNs with the global information sharing ability of Graph Neural Networks, but also maps semantic relationships between learnable class embeddings and corresponding spectrogram regions. We evaluate ATGNN on two audio tagging tasks, where it achieves 0.585 mAP on the FSD50K dataset and 0.335 mAP on the AudioSet-balanced dataset, achieving comparable results to Transformer based models with significantly lower number of learnable parameters.