发表机构
Prior Labs; Stanford University; NVIDIA; University of Freiburg; ELLIS Institute Tübingen（Prior Labs; 斯坦福大学; 英伟达; 弗赖堡大学; 图宾根ELLIS研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Prior Labs开源RelArena-$α$、TabPFN-Rel与RPI三款关系学习工具，解决领域内方法比较不可靠问题，TabPFN-Rel在RelArena-$α$暂居第一，为关系学习提供开放可复现的研究基础。
AI 中文摘要
本次Prior Labs在关系学习领域的首次发布，彰显了我们对开放科学的持续承诺。我们开源了三款软件，期望能推动该领域的研究向有意义的实际应用影响迈进，并计划基于社区反馈及与社区的合作来引导后续开发。鉴于尚处于开发早期，本次$α$版本面向研究人员与早期采用者从业者。过去数年里，关系学习领域涌现了各类数据集与任务，但社区尚未就这些任务上不同方法间可靠、可复现的比较方式达成共识。我们的$α$版本RelArena-$α$提供了一个统一框架，用于在RelBench v1上运行和比较基线模型，它借鉴了TabArena等成熟表格基准的思路，通过标准化数据加载、评估协议、调优机制以及对支持自定义调优的系统的支持来实现这一目标，我们计划与研究社区合作，进一步将RelArena-$α$发展为推动关系学习社区进步的催化剂。我们还发布了TabPFN-Rel的初始版本，这是一款专为TabPFN-3打造的关系学习工具。目前，TabPFN-Rel在RelArena-$α$的模型中排名第一，它在RDBLearn的基础上做出了关键改进；除排名外，TabPFN-Rel作为强基线模型，进一步佐证了在实际任务中，将关系数据库展平为单表的方法仍可与专用关系架构相媲美。为促进关系学习方法在研究与工业领域的应用，我们发布了关系预测接口（Relational Predictive Interface，RPI）的初始$α$版本，这是一个开源、与模型无关的接口，可让早期采用者轻松定义新数据库上的问题，并将RelArena-$α$中实现的任何模型（包括TabPFN-Rel）应用于这些问题。
英文摘要
This first release of Prior Labs in relational learning shows our continued commitment to open science. We open-source three pieces of software that we expect to accelerate research in the field towards meaningful real-world impact. We aim to steer further development based on feedback from, and in collaboration with, the community. Given the early stage of development, our $α$-release targets researchers and early-adopting practitioners. Over the past years, a variety of datasets and tasks for relational learning have emerged, but the community has not converged on a reliable, reproducible way to compare different methods on these tasks. Our $α$-release, RelArena-$α$, provides a unified framework for running and comparing baselines on RelBench v1 by standardizing data loading, evaluation protocols, tuning regimes, and support for systems with custom tuning, inspired by established tabular benchmarks such as TabArena. We plan to work with the research community to further develop RelArena-$α$ into a catalyst for progress in the relational learning community. We release the initial version of TabPFN-Rel, a purpose-built relational harness for TabPFN-3. Currently ranked first among models on RelArena-$α$, TabPFN-Rel makes key improvements upon RDBLearn. Beyond its ranking, TabPFN-Rel serves as a strong baseline, adding to the growing evidence that flattening a relational database into a single table remains competitive with specialized relational architectures on real-world tasks. To facilitate adoption of relational learning methods in research and industry, we release an initial $α$-version of our Relational Predictive Interface, RPI, an open-source, model-agnostic interface that enables early adopters to easily define problems on new databases and apply any model implemented in RelArena-$α$, including TabPFN-Rel, to these problems.
