9 papers · 1 filter
NodeGround: A Node Classification Benchmark in the Graph Foundation Model Era
Jinmo Lee, Dooho Lee, Minho Jeong +1
Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality alongside computational cost.…
Molecular Property Prediction under Structural Shift with Tabular Foundation Models
Jinmo Lee, Dooho Lee, Minho Jeong +1
Predicting molecular properties for compounds that differ structurally from labeled training molecules is important for drug discovery and materials design. Tabular foundation mode…
TaskBridge: Bridging Unsupervised Tabular Anomaly Detection and In-Context Learning via Virtual Tasks
Doyun Choi, Dooho Lee, Jaemin Yoo
Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods rely on dataset-specific trai…
Causilo Technical Report
Minyong Cho, Minho Jeong, Dooho Lee +2
We introduce Causilo, a tabular foundation model (TFM) that combines frontier predictive performance with exceptionally fast inference. On TabArena, Causilo achieves 1785.4 Elo, at…
Node4All: Learning Node Representation Beyond Datasets
Dooho Lee, Jaemin Yoo
Node representation learning has advanced rapidly, yet most existing methods rely on per-dataset training and hyperparameter tuning. This dataset-specific optimization comes from t…
Bounded Context Management for Tabular Foundation Models on Stream Learning
Jinmo Lee, Doyun Choi, Moongi Choi +1
Tabular stream learning requires predictions on sequentially arriving examples under distribution shift. While standard methods adapt by updating model states, tabular foundation m…
Generalizing Multi-Scale Time-Series Modeling with a Single Operator
Cheonwoo Lee, Dooho Lee, Doyun Choi +1
Multi-scale modeling has emerged as an effective design principle for time-series forecasting by capturing temporal dynamics at multiple resolutions. As no principled foundation ha…
Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
Chaewoon Bae, Doyun Choi, Jaehyun Lee +1
Few-shot node classification on hypergraphs requires models that generalize from scarce labels while capturing high-order structures. Existing hypergraph neural networks (HNNs) eff…
Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
Dooho Lee, Myeong Kong, Sagad Hamid +2
We revisit DropEdge, a data augmentation technique for GNNs which randomly removes edges to expose diverse graph structures during training. While being a promising approach to eff…