EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
Detecting Statistical Interactions from Neural Network Weights
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpreting its learned weights. Depending on the desired interactions, our method can achieve significantly better or similar interaction detection performance compared to the state-of-the-art without searching an exponential solution space of possible interactions. We obtain this accuracy and efficiency by observing that interactions between input features are created by the non-additive effect of nonlinear activation functions, and that interacting paths are encoded in weight matrices. We demonstrate the performance of our method and the importance of discovered interactions via experimental results on both synthetic datasets and real-world application datasets.
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
TabDistill distills feature interactions from tabular foundation models via post-hoc attribution and inserts them into GAMs, yielding consistent predictive gains.
Introduces M-information as a scalable measure of higher-order information integration in multivariate time series, computed via convex optimization and tested on neuronal and neuroimaging data.
citing papers explorer
-
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
-
Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models
TabDistill distills feature interactions from tabular foundation models via post-hoc attribution and inserts them into GAMs, yielding consistent predictive gains.
-
A scalable estimator of higher-order information in complex dynamical systems
Introduces M-information as a scalable measure of higher-order information integration in multivariate time series, computed via convex optimization and tested on neuronal and neuroimaging data.