English
Related papers

Related papers: Exploring Transformer Backbones for Heterogeneous …

200 papers

Previous work on Universal Transformers (UTs) has demonstrated the importance of parameter sharing across layers. By allowing recurrence in depth, UTs have advantages over standard Transformers in learning compositional generalizations, but…

Machine Learning · Computer Science 2024-10-15 Róbert Csordás , Kazuki Irie , Jürgen Schmidhuber , Christopher Potts , Christopher D. Manning

The credibility revolution advances the use of research designs that permit identification and estimation of causal effects. However, understanding which mechanisms produce measured causal effects remains a challenge. The dominant current…

Econometrics · Economics 2026-04-08 Jiawei Fu , Tara Slough

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Computation and Language · Computer Science 2021-02-17 Mikhail S. Burtsev , Yuri Kuratov , Anton Peganov , Grigory V. Sapunov

This work proposes the M3E2, a multi-task learning neural network model to estimate the effect of multiple treatments. In contrast to existing methods, M3E2 can handle multiple treatment effects applied simultaneously to the same unit,…

Machine Learning · Computer Science 2023-01-09 Raquel Aoki , Yizhou Chen , Martin Ester

Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in their decision-making processes would substantially enhance…

Quantitative Methods · Quantitative Biology 2025-06-18 Laurence Freeman , Philip Shamash , Vinam Arora , Caswell Barry , Tiago Branco , Eva Dyer

As estimation of Heterogeneous Treatment Effect (HTE) is increasingly adopted across a wide range of scientific and industrial applications, the treatment action space can naturally expand, from a binary treatment variable to a structured…

Machine Learning · Computer Science 2025-07-09 Jennifer Y. Zhang , Shuyang Du , Will Y. Zou

Transformer-based neural networks have achieved state-of-the-art task performance in a number of machine learning domains including natural language processing and computer vision. To further improve their accuracy, recent work has explored…

Machine Learning · Computer Science 2022-09-01 Salar Latifi , Saurav Muralidharan , Michael Garland

Robust estimation of heterogeneous treatment effects is a fundamental challenge for optimal decision-making in domains ranging from personalized medicine to educational policy. In recent years, predictive machine learning has emerged as a…

Machine Learning · Statistics 2025-06-23 Maximilian Schuessler , Erik Sverdrup , Robert Tibshirani

Tabular data remains a challenging domain for generative models. In particular, the standard Variational Autoencoder (VAE) architecture, typically composed of multilayer perceptrons, struggles to model relationships between features,…

Machine Learning · Computer Science 2026-01-29 Aníbal Silva , Moisés Santos , André Restivo , Carlos Soares

Estimating treatment effects from observational data is challenging due to two main reasons: (a) hidden confounding, and (b) covariate mismatch (control and treatment groups not having identical distributions). Long lines of works exist…

Machine Learning · Computer Science 2025-04-30 Praharsh Nanavati , Ranjitha Prasad , Karthikeyan Shanmugam

We consider the problem of extrapolating treatment effects across heterogeneous populations (``sites"/``contexts"). We consider an idealized scenario in which the researcher observes cross-sectional data for a large number of units across…

Econometrics · Economics 2025-10-03 Konrad Menzel

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i.e. feed-forward network) of transformer. However, scaling the cross-token module (i.e. self-attention) is…

Machine Learning · Computer Science 2022-01-17 Yuxuan Lou , Fuzhao Xue , Zangwei Zheng , Yang You

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Conditional Average Treatment Effects (CATE) estimation is one of the main challenges in causal inference with observational data. In addition to Machine Learning based-models, nonparametric estimators called meta-learners have been…

Machine Learning · Statistics 2023-06-06 Naoufal Acharki , Ramiro Lugo , Antoine Bertoncello , Josselin Garnier

Recently, there is a growing interest in applying Transfer Entropy (TE) in quantifying the effective connectivity between artificial neurons. In a feedforward network, the TE can be used to quantify the relationships between neuron output…

Machine Learning · Computer Science 2024-04-05 Adrian Moldovan , Angel Caţaron , Răzvan Andonie

Explainable machine learning significantly improves the transparency of deep neural networks. However, existing work is constrained to explaining the behavior of individual model predictions, and lacks the ability to transfer the…

Estimating heterogeneous treatment effects with machine learning has attracted substantial attention in both academic research and industrial practice. However, the two communities often evaluate models under markedly different conditions.…

Machine Learning · Computer Science 2026-05-26 George Panagopoulos

Deep learning models such as the Transformer are often constructed by heuristics and experience. To provide a complementary foundation, in this work we study the following problem: Is it possible to find an energy function underlying the…

Machine Learning · Computer Science 2023-02-28 Yongyi Yang , Zengfeng Huang , David Wipf

Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory…

Computer Vision and Pattern Recognition · Computer Science 2023-01-04 Yuexiang Li , Yawen Huang , Nanjun He , Kai Ma , Yefeng Zheng