paper-with-me

Papers

Mixed-effects transformers for hierarchical adaptation

2022-05-03 · Julia White, Noah Goodman, Robert Hawkins

Language use differs dramatically from context to context. To some degree, modern language models like GPT-3 are able to account for such variance by conditioning on a string of previous input text, or prompt. Yet prompting is ineffective when contexts are sparse, out-of-sample, or extra-textual; for instance, accounting for when and where the text was produced or who produced it. In this paper, we introduce the mixed-effects transformer (MET), a novel approach for learning hierarchically-structured prefixes -- lightweight modules prepended to the input -- to account for structured variation. Specifically, we show how the popular class of mixed-effects models may be extended to transformer-based architectures using a regularized prefix-tuning procedure with dropout. We evaluate this approach on several domain-adaptation benchmarks, finding that it efficiently adapts to novel contexts with minimal data while still effectively generalizing to unseen contexts.

📄 PDF Abstract BibTeX arXiv:2205.01749

Code (1)

juliaiwhite/mixed-effects-transformers 공식 구현 pytorch

Tasks

Domain Adaptation

Methods 이 논문이 사용한 방법론

15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

2022-05-26 · CVPR 2023 1 · Jihao Liu, Xin Huang, Jinliang Zheng, Yu Liu 외

In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical Vision Transformers. Existing masked image modeling (MIM) methods for …

Image ClassificationObject DetectionRepresentation LearningSemantic Segmentation

metabeta -- A fast neural model for Bayesian mixed-effects regression

2025-10-08 · Alex Kipnis, Marcel Binz, Eric Schulz arxiv

Hierarchical data with multiple observations per group is ubiquitous in empirical sciences and is often analyzed using mixed-effects regression. In such models, Bayesian inference gives an estimate of uncertainty but is …

Bayesian Inference

Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning

2024-06-12 · Yizhe Huang, Anji Liu, Fanqi Kong, Yaodong Yang 외

Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchi…

Decision MakingMulti-agent Reinforcement Learning

Hierarchical Embedded Bayesian Additive Regression Trees

2022-04-14 · Bruna Wundervald, Andrew Parnell, Katarina Domijan

We propose a simple yet powerful extension of Bayesian Additive Regression Trees which we name Hierarchical Embedded BART (HE-BART). The model allows for random effects to be included at the terminal node level of a set …

regression

Simulation-based inference for stochastic nonlinear mixed-effects models with applications in systems biology

2025-04-15 · Henrik Häggström, Sebastian Persson, Marija Cvijovic, Umberto Picchini

The analysis of data from multiple experiments, such as observations of several individuals, is commonly approached using mixed-effects models, which account for variation between individuals through hierarchical represe…

Bayesian InferenceSociology