arXiv：cs.LG· Patrick Stinson, Nikolaus Kriegeskorte·· 4 小时前AI 评分32
双原始图 VAE 用于噪声标签聚合
Dual-Primal Graph VAEs for Noisy Label Aggregation
AI 导读
研究者提出一种图 VAE 架构，其解码器与编码器分别在图数据集及其对偶图的邻接图上进行基于 GAT 的消息传递，将真实标签作为隐变量，无需训练单独分类器即可实现无监督表示学习。该模型在众包基准上取得 SOTA 性能。作者还展示了通过对原众包图进行增强以引入由噪声标签训练的神经网络分类器表示等辅助信息，可在测试时大幅提升分类性能。
正文
Abstract:Inferring the ground-truth from noisy crowdsourced labels is an important theoretical and practical problem. Neural network-based methods offer an alternative to classical Bayesian models which require specifying a family of generative models used for inference. However, current models either still rely on fairly simple generative models for inference or require pseudo-labels or synthetic data to train the aggregate classifier. We propose a graph VAE architecture in which the decoder and encoder use GAT-based message passing on the adjacency graph of a crowdsourced dataset and its dual, respectively. The ground-truth labels are treated as latent variables, enabling unsupervised representation learning without needing to train a separate classifier. We show our model achieves state of the art performance on crowdsourcing benchmarks. We then demonstrate the generality of our approach by showing how the original crowdsourcing graph can be augmented to incorporate side information such as representations from neural network classifiers trained on the noisy labels to substantially boost their classification performance at test time.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2608.11473 [cs.LG] |
| (or arXiv:2608.11473v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2608.11473 arXiv-issued DOI via DataCite |
Submission history
From: Patrick Stinson [view email]
[v1]
Tue, 11 Aug 2026 22:24:16 UTC (73 KB)
[v2]
Tue, 6 Oct 2026 22:41:43 UTC (219 KB)
来源：arXiv：cs.LG · arxiv.org