We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the $p(y \mid x, D_{\mathrm{context}})$ objective of conventional tabular PFNs, it is designed around learning $p(x, y \mid D_{\mathrm{context}})$, a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic datasets generated by structural causal models (SCMs) spanning diverse graph structures, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.
This tutorial presents a systematic overview of this emerging paradigm of tabular foundation models, which treats tables as a common representation that can capture information from tabular data, time series, and graphs within a shared learning framework.
Peng Cui, Xing-Xuan Zhang, Han-Jia Ye et al.· Proceedings of the 32nd ACM...· 0 citations
A novel self-supervised framework for relational reasoning over RDBs that treats context sparsity as a controllable curriculum variable and leverages it to induce a progressive shift from semantic-dominant inference to structure-aware relational reasoning.
Yujie Tian, Kun Zhang, Qiu-Yuan Li et al.· Proceedings of the 32nd ACM...· 0 citations
Modern data are increasingly represented and utilized as interconnected networks, including collaboration graphs, multi-relational user–item interactions, and schema-less knowledge graphs that support retrieval-augmented generation pipelines. While graph analytics has become a key foundation for intelligent data mining...
Yao Hu, Qian Huang· Innovation Discovery· 0 citations
Graph representation learning has emerged as a foundational discipline within modern data science, essential for modeling the complex relational systems ubiquitous in domains from social networks to bioinformatics. However, conventional approaches, particularly Graph Neural Networks (GNN), exhibit significant limitatio...
Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeated costs and effort. Graph in-context learning (ICL) avoids this by using a single pretrained model to predict unknown node labels directly from labeled context nodes. E...
Dooho Lee, Jin-Mo Lee, Minho Jeong et al.· 0 citations
Graph modeling, a crucial task for representing complex relationships in graph-structured data, has achieved significant success in recent years. However, current graph modeling methods rely on traditional Graph Neural Networks and pre-training approaches to implicitly learn the underlying relational structure of graph...
Thanh-Dat Truong, Sarah Alharbi, Susan Gauch et al.· 0 citations
