LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913669465505792 |
|---|---|
| author | Singh, Shubhr Benetos, Emmanouil Phan, Huy Stowell, Dan |
| author_facet | Singh, Shubhr Benetos, Emmanouil Phan, Huy Stowell, Dan |
| contents | Transformers have set new benchmarks in audio processing tasks, leveraging self-attention mechanisms to capture complex patterns and dependencies within audio data. However, their focus on pairwise interactions limits their ability to process the higher-order relations essential for identifying distinct audio objects. To address this limitation, this work introduces the Local- Higher Order Graph Neural Network (LHGNN), a graph based model that enhances feature understanding by integrating local neighbourhood information with higher-order data from Fuzzy C-Means clusters, thereby capturing a broader spectrum of audio relationships. Evaluation of the model on three publicly available audio datasets shows that it outperforms Transformer-based models across all benchmarks while operating with substantially fewer parameters. Moreover, LHGNN demonstrates a distinct advantage in scenarios lacking ImageNet pretraining, establishing its effectiveness and efficiency in environments where extensive pretraining data is unavailable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03464 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging Singh, Shubhr Benetos, Emmanouil Phan, Huy Stowell, Dan Sound Artificial Intelligence Audio and Speech Processing Transformers have set new benchmarks in audio processing tasks, leveraging self-attention mechanisms to capture complex patterns and dependencies within audio data. However, their focus on pairwise interactions limits their ability to process the higher-order relations essential for identifying distinct audio objects. To address this limitation, this work introduces the Local- Higher Order Graph Neural Network (LHGNN), a graph based model that enhances feature understanding by integrating local neighbourhood information with higher-order data from Fuzzy C-Means clusters, thereby capturing a broader spectrum of audio relationships. Evaluation of the model on three publicly available audio datasets shows that it outperforms Transformer-based models across all benchmarks while operating with substantially fewer parameters. Moreover, LHGNN demonstrates a distinct advantage in scenarios lacking ImageNet pretraining, establishing its effectiveness and efficiency in environments where extensive pretraining data is unavailable. |
| title | LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.03464 |