迈向能量前沿异质中微子探测器的风格化模型:通过自监督预训练
Towards foundation-style models for energy-frontier heterogeneous neutrino detectors via self-supervised pre-training
AI总结:
本文提出一种稀疏ViT框架,通过自监督预训练学习异质探测器数据的可重用表示,提升中微子风味和charm夸克识别、动量回归和顶点重建性能。
摘要:
基于加速器的中微子物理正进入能量前沿阶段,其中相互作用达到TeV量级,产生异常密集且重叠的探测器信号。在该阶段,传统重建方法的事件解释变得不切实际,尤其当标记数据稀缺且分析涵盖多样下游目标时。本文提出一种稀疏ViT框架,通过自监督预训练学习异质探测器数据的可重用表示。自监督预训练结合了掩码自动编码器重建与关系体素级目标,用于层次、幽灵和粒子识别,所得共享编码器随后在分类和回归任务中联合微调。在LHC提出的FASERCal概念模拟事件上评估,发现预训练在中微子风味和charm夸克识别、动量回归和顶点重建方面优于从头训练,添加关系目标在最复杂的拓扑通道中进一步提升性能。可解释性分析进一步显示预训练产生更结构化的潜在空间,而探测器子系统消融恢复了物理上合理的通道依赖性角色。数据效率研究显示,使用约10^3个标记事件,预训练编码器已能匹配随机初始化模型在数量级更多数据上的风味分类性能。学习的表示也有效转移到公开可用的基准上,涵盖不同的探测器技术和能量尺度,匹配或超过已发布的基线。这些结果支持在多模态探测器数据上进行自监督预训练作为可扩展的路线,以实现中微子和粒子探测器分析的可重用表示。
英文摘要:
Accelerator-based neutrino physics is entering an energy-frontier regime in which interactions reach the TeV scale and produce exceptionally dense, overlapping detector signatures. In this regime, event interpretation becomes impractical for conventional reconstruction approaches, particularly when labelled data are scarce and the analysis spans diverse downstream objectives. We present a sparse ViT framework for learning reusable representations from heterogeneous detector data. Self-supervised pre-training combines masked autoencoder reconstruction with relational voxel-level objectives for hierarchy, ghost and particle identification, and the resulting shared encoder is then jointly fine-tuned across classification and regression tasks. Evaluated on simulated events from the proposed FASERCal concept at the LHC, we find that pre-training consistently improves neutrino flavour and charm-quark identification, momentum regression, and vertex reconstruction over training from scratch, with the addition of relational objectives yielding further gains in the most topologically complex channels. Interpretability analyses further show that pre-training yields a more structured latent space, while detector-subsystem ablations recover physically plausible channel-dependent roles for the heterogeneous inputs. A data-efficiency study shows that, with roughly $10^3$ labelled events, the pre-trained encoder already matches the flavour-classification performance of a randomly initialised model trained on an order of magnitude more data. The learned representations also transfer effectively to publicly available benchmarks spanning different detector technologies and energy scales, matching or exceeding published baselines. These results support self-supervised pre-training on multimodal detector data as a scalable route towards reusable representations for neutrino and particle-detector analysis.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。