用图神经网络捕捉音频中更高阶关系，比Transformer更高效
LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging
- 构建局部邻域与模糊聚类的高阶图结构，增强音频特征表达
- 在3个数据集上超越Transformer，参数量减少显著
- 适合缺乏大规模预训练数据的音频分类场景
Transformer在音频处理任务中取得新突破，依赖自注意力机制捕捉复杂模式与依赖关系。然而，其仅关注成对交互，难以建模识别音频对象所必需的高阶关系。为此，本文提出局部-高阶图神经网络（LHGNN），通过融合局部邻域信息与模糊C均值聚类生成的高阶数据，提升特征理解能力，捕捉更广泛的音频关系。在三个公开音频数据集上的评估表明，LHGNN在所有基准测试中均优于基于Transformer的模型，且参数量显著减少。此外，该模型在缺乏ImageNet预训练的情况下仍表现优异，证明其在无大量预训练数据环境中的有效性与高效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。