paper-with-me

Papers

Graph Mixing Additive Networks

2025-09-28 · Maya Bechler-Speicher, Andrea Zerio, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs arxiv

We introduce GMAN, a flexible, interpretable, and expressive framework that extends Graph Neural Additive Networks (GNANs) to learn from sets of sparse time-series data. GMAN represents each time-dependent trajectory as a directed graph and applies an enriched, more expressive GNAN to each graph. It allows users to control the interpretability-expressivity trade-off by grouping features and graphs to encode priors, and it provides feature, node, and graph-level interpretability. On real-world datasets, including mortality prediction from blood tests and fake-news detection, GMAN outperforms strong non-interpretable black-box baselines while delivering actionable, domain-aligned explanations.

📄 PDF Abstract BibTeX arXiv:2509.23923

Code (0)

등록된 구현이 없습니다.

Tasks

Mortality Prediction

Similar Papers 제목 키워드 기반

Gauge-Equivariant Graph Networks via Self-Interference Cancellation

2025-11-20 · Yoonhyuk Choi, Jiho Choi, Jiwoo Kang arxiv

Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We propose a \textbf{G}auge-\textbf{E}quivariant Graph Network with \textb…

Generalization for slowly mixing processes

2023-04-28 · Andreas Maurer

A bound uniform over various loss-classes is given for data generated by stationary and phi-mixing processes, where the mixing time (the time needed to obtain approximate independence) enters the sample complexity only i…

Free Component Analysis: Theory, Algorithms & Applications

2019-05-05 · Hao Wu, Raj Rao Nadakuditi

We describe a method for unmixing mixtures of freely independent random variables in a manner analogous to the independent component analysis (ICA) based method for unmixing independent random variables from their additi…

Causal Representation Learning from General Environments under Nonparametric Mixing

2026-04-26 · Ignavier Ng, Shaoan Xie, Xinshuai Dong, Peter Spirtes 외 arxiv

Causal representation learning aims to recover the latent causal variables and their causal relations, typically represented by directed acyclic graphs (DAGs), from low-level observations such as image pixels. A prevaili…

Representation Learning

Restless dependent bandits with fading memory

2019-06-25 · Oleksandr Zadorozhnyi, Gilles Blanchard, Alexandra Carpentier

We study the stochastic multi-armed bandit problem in the case when the arm samples are dependent over time and generated from so-called weak $\cC$-mixing processes. We establish a $\cC-$Mix Improved UCB agorithm and pro…