AutoManifold：基于流形嵌入的智能体式数据可视化算法设计
AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding
AI 导读
研究者提出 AutoManifold，一个由多智能体大语言模型驱动的算法生成流水线，可按用户指定的结构保持偏好自动组合新的流形嵌入算法。它在统一评估环境下与 t-SNE、UMAP、PaCMAP 三种 SOTA 方法在真实数据集上对比，生成的算法能在不破坏数据内在结构的前提下更好地满足用户指定属性。代码已开源，论文被 NeurIPS 2026 接收。
正文 · 原文
Abstract:Manifold embedding for data visualisation is dominated by a small set of hand-designed state-of-the-art (SOTA) algorithms. Their design targets are fixed at development time, resulting in inflexible algorithmic behaviour that cannot be readily steered towards user-specified structural priorities. Hand-designing new embedding algorithms to address user priority requires highly specialised expertise and is time consuming. To address autonomous algorithm design tailored to user preference, we introduce an agentic algorithm generation pipeline AutoManifold. It composes new manifold embedding algorithms from a constrained vocabulary of affinity, cost, and optimisation primitives, supported by multi-agent large-language-model (LLM) orchestration. AutoManifold conditions every stage of its design on user-specified structural preservation preferences, and iteratively refines the algorithm configuration through an LLM-guided, metric-grounded iterative loop. We compare the generated algorithms against the three strongest and most frequently used SOTA methods (t-SNE, UMAP, and PaCMAP) on real-world datasets spanning different difficulty regimes under identical evaluation infrastructure. The results demonstrate that LLM-driven, priority-conditioned algorithm synthesis can move beyond hyperparameter tuning, producing genuinely new algorithms that outperform traditional hand-designed methods in their ability to steer towards user-specified properties without compromising the intrinsic structure in the original data. The code of AutoManifold is available at this https URL.
| Comments: | Accepted at NeurIPS 2026 (40th Conference on Neural Information Processing Systems). 37 pages, 5 figures. Code: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13710 [cs.AI] |
| (or arXiv:2611.13710v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13710 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Burak Susam [view email]
[v1]
Tue, 10 Nov 2026 08:03:15 UTC (3,345 KB)
来源：arXiv cs.AI · arxiv.org