推進開放且可重現的關聯式學習：RelArena-α、TabPFN-Rel 與 RPI
Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPI
August 17, 2026
作者: Adrian Hayler, Klemens Flöge, Alan Arazi, Rishabh Ranjan, Jure Leskovec, Felix Birkel, Brendan Roof, Anurag Garg, Kristina Collins, Lydia Sidhoum, Jonas Kübler, Siyuan Guo, Oscar Key, Jan Hendrik Metzen, Rylee Grace, David Salinas, Arthur Cahu, Simon Bing, Benjamin Jäger, Tuana Çelik, Mihir Manium, Vitor Monteiro, Jake Robertson, Jerry Chen, Eliott Kalfon, Tomás Pereda, Lilly Wehrhahn, Dominik Safaric, Tobias Schroeder, Georg Grab, Diana Kriuchkova, Clara Cornu, Philipp Singer, Nick Erickson, Vahid Balazadeh, Marie Salmon, Simone Alessi, Kürşat Kaya, Philipp Jund, Léo Grinsztajn, Yann LeCun, Bernhard Schölkopf, Madelon Hulsebos, Lennart Purucker, Sauraj Gambhir, Frank Hutter, Noah Hollmann
cs.AI
摘要
Prior Labs 在關聯式學習領域的首次發布，展現了我們對開放科學的持續承諾。我們開源了三項軟體，期望能加速該領域的研究，帶來具意義的實際影響。我們旨在根據社群的回饋，並與社群合作，來引導後續的發展。鑑於目前的開發仍處於早期階段，我們的 α 版本主要針對研究人員與早期採用的實踐者。
過去幾年來，雖然湧現了各式各樣的關聯式學習資料集與任務，但社群尚未就如何在這些任務上以可靠且可重現的方式比較不同方法達成共識。我們的 α 版本 RelArena-α 提供了一個統一框架，用於在 RelBench v1 上執行與比較基線模型，透過標準化資料載入、評估協議、調參機制，以及對自訂調參系統的支援；此框架的設計參考了如 TabArena 等已建立的表格型基準。我們計劃與研究社群合作，進一步將 RelArena-α 發展為推動關聯式學習社群進步的催化劑。
我們發布了 TabPFN-Rel 的初始版本，這是專為 TabPFN-3 設計的關聯式工具框架。TabPFN-Rel 目前在 RelArena-α 的模型排名中位居第一，並相較於 RDBLearn 做出了關鍵改進。除了排名之外，TabPFN-Rel 也作為一個強大的基線，進一步佐證了將關聯式資料庫攤平為單一表格的做法，在真實世界的任務中仍可與專門的關聯式架構一較高下。
為了促進關聯式學習方法在研究與產業中的採用，我們發布了關聯式預測介面 RPI 的初始 α 版本。RPI 是一個開源、與模型無關的介面，讓早期採用者能夠輕鬆地在新資料庫上定義問題，並將 RelArena-α 中實作的任何模型（包括 TabPFN-Rel）應用於這些問題。
English
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.