arXiv cs.AI· Muhammed Faruk Aytin, Zehra Demir, Alper Unal, Julian Marshall, Gozde Unal·· 9 天前AI 评分22
NCAM：异构传感器偏差下可识别的无监督多传感器回归
Neural Conjugate Aggregation: Identifiable Unsupervised Multi-Sensor Regression under Heterogeneous Sensor Bias
AI 导读
研究者提出神经共轭聚合模型（NCAM），一种结合神经网络与共轭高斯推断的分层贝叶斯框架，用于无真值标签下的多源传感器数据融合。NCAM 以情境协变量为条件学习各源的偏差与可靠性，通过传感器锚定与方差正则化解决结构不可识别问题，并引入局部自适应蒙特卡洛共形预测给出带覆盖保证的异方差预测区间。在合成与真实空气质量数据集上，其预测精度与不确定性校准优于均值聚合、概率 PCA 和卡尔曼滤波等无监督基线。
正文 · 原文
Abstract:We study regression-based data fusion under uncertainty, where multiple noisy and biased measurement sources are available but ground-truth labels are absent during training. This setting arises in sensor networks, simulation ensembles, and scientific monitoring systems where supervision is costly or infeasible. We propose the Neural Conjugate Aggregation Model (NCAM), a hierarchical Bayesian framework that combines neural networks with conjugate Gaussian inference for unsupervised multi-source fusion. NCAM learns source-specific bias and reliability conditioned on contextual covariates, yielding an analytically tractable posterior over a latent target variable with decomposed epistemic and aleatoric uncertainty. Structural non-identifiability is resolved through sensor anchoring and variance regularization, enabling stable and interpretable posterior aggregation. To complement Bayesian uncertainty with finite-sample guarantees, we integrate locally adaptive Monte Carlo conformal prediction, producing heteroscedastic prediction intervals with coverage guarantees under exchangeability assumptions. Experiments on synthetic and real-world air-quality datasets demonstrate improved predictive accuracy and well-calibrated uncertainty compared to unsupervised baselines, including mean aggregation, probabilistic PCA, and Kalman filtering.
| Comments: | 10 pages |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| MSC classes: | 62F15, 62J02, 68T07, 62M20 |
| ACM classes: | I.2.6; G.3; I.5.1 |
| Cite as: | arXiv:2606.22200 [cs.LG] |
| (or arXiv:2606.22200v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.22200 arXiv-issued DOI via DataCite |
Submission history
From: Muhammed Faruk Aytin [view email]
[v1]
Sat, 20 Jun 2026 19:30:21 UTC (238 KB)
[v2]
Thu, 8 Oct 2026 07:32:13 UTC (238 KB)
来源：arXiv cs.AI · arxiv.org