arXiv：cs.AI· Rishav Mukherjee, Jeffrey Ahearn Thompson·· 4 小时前
JEDI-net：联合嵌入与动态集成网络，通过聚类 SHAP 值提升神经网络性能
Joint Embedding with Dynamic Integration network (JEDI-net)
AI 导读
JEDI-net（Joint Embedding with Dynamic Integration Network）是一种统一架构，在优化过程中定期聚类 SHAP 值以识别具有相似特征重要性模式的潜在子群，并将其身份直接嵌入网络，使预测能适应每个观测的预测结构。
正文
Abstract:Deep learning has become the dominant form of machine learning due in part, to its ability to automatically engineer complex meta features from data. However, even deep learning features can perform erratically because of unobserved latent factors. incorporating latent factor information explicitly, can improve performance by letting the model alter its behavior based on such inferred factors. Because neural networks often capture such complexity inherently, external clustering of the original feature space offers limited benefit. clustering observations by feature importance profiles, rather than raw features, offers a principled way to uncover latent structure, since observations with similar importance patterns may share predictive dynamics. In a prior work, Feature Oriented Representation with Clustering and Explanation (FORCE) we showed that this approach measurably improved neural network performance. In this article, we present JEDI-net(Joint Embedding with Dynamic Integration Network) a unified architecture that periodically clusters SHAP values during optimization to identify latent subgroups with similar feature importance patterns, embed their identities directly into the network, allowing predictions to adapt to each observations predictive structure.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17314 [cs.LG] |
| (or arXiv:2610.17314v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17314 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rishav Mukherjee [view email]
[v1]
Mon, 12 Oct 2026 19:13:24 UTC (406 KB)
来源：arXiv：cs.AI · arxiv.org