Metraipolis › archive › dc_f161ad2d1890
Dual-Primal Graph VAEs for Noisy Label Aggregation — arXiv:2608.11473
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11473
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:39:47.299Z
- SHA-256 of the archived text
7b7f1fe1a262aa7c9793db3f5039301473f6e860054d88757cfa30d6cd90bd87- Stable URL of this page
https://metraipolis.com/documento/dc_f161ad2d1890
How to cite
Dual-Primal Graph VAEs for Noisy Label Aggregation — arXiv:2608.11473 — arXiv (en), https://arxiv.org/abs/2608.11473 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f161ad2d1890 (Metraipolis archive dc_f161ad2d1890, sha256 7b7f1fe1a262aa7c9793db3f5039301473f6e860054d88757cfa30d6cd90bd87)
BibTeX
@misc{dcf161ad2d1890,
title = {Dual-Primal Graph VAEs for Noisy Label Aggregation — arXiv:2608.11473},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11473},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f161ad2d1890; sha256 7b7f1fe1a262aa7c9793db3f5039301473f6e860054d88757cfa30d6cd90bd87},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11473. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.11473 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:18:32.467Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).