59 citations · 121 across the 57 of their papers we have counts for
21 papers · 1 filter
Evolving Executable Pipeline Programs for AutoML with Language Models
Sofoklis Kitharidis, Cor J. Veenman, Jan N. van Rijn +2
Automated machine learning (AutoML) systems search for pipelines within a space of preprocessing operators, learners, and hyper-parameters specified in advance: they can select and…
Every Component Is a Lookup: One Linear Graph for Interaction, Composition and Attribution
Po-Kai Chen, Aske Plaat, Niki van Stein
Interpretability methods for transformers are typically built around separate questions: which components interact, how information routes to the output, and which input tokens con…
From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors
Qi Huang, Furong Ye, Ananta Shahane +2
Large Language Models (LLMs) have already been widely adopted for automated algorithm design, demonstrating strong abilities in generating and evolving algorithms across various fi…
Mechanistic Interpretability for Transformer-based Time Series Classification
Matīss Kalnāre, Sofoklis Kitharidis, Thomas Bäck +1
Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their…
Visual Model Selection using Feature Importance Clusters in Fairness-Performance Similarity Optimized Space
Sofoklis Kitharidis, Cor J. Veenman, Thomas Bäck +1
In the context of algorithmic decision-making, fair machine learning methods often yield multiple models that balance predictive fairness and performance in varying degrees. This d…
Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
Zhong Li, Qi Huang, Yuxuan Zhu +4
We introduce Time-Conditioned Contraction Matching (TCCM), a novel method for semi-supervised anomaly detection in tabular data. TCCM is inspired by flow matching, a recent generat…