English
Related papers

Related papers: Exploring Transformer Backbones for Heterogeneous …

200 papers

Temporal information extraction (IE) aims to extract structured temporal information from unstructured text, thereby uncovering the implicit timelines within. This technique is applied across domains such as healthcare, newswire, and…

Computation and Language · Computer Science 2025-04-11 Xin Su , Phillip Howard , Steven Bethard

Current neural networks architectures are many times harder to train because of the increasing size and complexity of the used datasets. Our objective is to design more efficient training algorithms utilizing causal relationships inferred…

Machine Learning · Computer Science 2021-05-03 Adrian Moldovan , Angel Caţaron , Răzvan Andonie

For counterfactual policy evaluation, it is important to ensure that treatment parameters are relevant to policies in question. This is especially challenging under unobserved heterogeneity, as is well featured in the definition of the…

Econometrics · Economics 2023-08-08 Sukjin Han , Shenshen Yang

In recent years, with the rapid development of science and technology, heterogeneous treatment effects have emerged as a focal research topic in statistics, econometrics, and sociology. This paper investigates HTE through semiparametric…

Methodology · Statistics 2025-07-21 Jichang Yu , Wenjing Chang , Peichao Yu , Lijun Chen , Yuanshan Wu

We study the problem of inferring heterogeneous treatment effects from time-to-event data. While both the related problems of (i) estimating treatment effects for binary or continuous outcomes and (ii) predicting survival outcomes have been…

Machine Learning · Computer Science 2022-01-25 Alicia Curth , Changhee Lee , Mihaela van der Schaar

Learning low-dimensional representation for large number of products present in an e-commerce catalogue plays a vital role as they are helpful in tasks like product ranking, product recommendation, finding similar products, modelling…

Information Retrieval · Computer Science 2022-12-08 Lakshya Kumar , Sreekanth Vempati

We propose expanding the shared Transformer module to produce and initialize Transformers of varying depths, enabling adaptation to diverse resource constraints. Drawing an analogy to genetic expansibility, we term such module as learngene.…

Artificial Intelligence · Computer Science 2023-12-21 Shiyu Xia , Miaosen Zhang , Xu Yang , Ruiming Chen , Haokun Chen , Xin Geng

We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings. Our approach utilizes a…

Machine Learning · Statistics 2025-06-09 Toru Shirakawa , Yi Li , Yulun Wu , Sky Qiu , Yuxuan Li , Mingduo Zhao , Hiroyasu Iso , Mark van der Laan

As an important problem in causal inference, we discuss the estimation of treatment effects (TEs). Representing the confounder as a latent variable, we propose Intact-VAE, a new variant of variational autoencoder (VAE), motivated by the…

Machine Learning · Statistics 2022-04-22 Pengzhou Wu , Kenji Fukumizu

Neural operator learning models have emerged as very effective surrogates in data-driven methods for partial differential equations (PDEs) across different applications from computational science and engineering. Such operator learning…

Machine Learning · Computer Science 2024-05-30 Benjamin Shih , Ahmad Peyvan , Zhongqiang Zhang , George Em Karniadakis

This paper establishes sufficient conditions for the identification of the marginal treatment effects with multivalued treatments. Our model is based on a multinomial choice model with utility maximization. Our MTE generalizes the MTE…

Econometrics · Economics 2024-12-30 Toshiki Tsuda

Multimodal language analysis is a burgeoning field of NLP that aims to simultaneously model a speaker's words, acoustical annotations, and facial expressions. In this area, lexicon features usually outperform other modalities because they…

Computation and Language · Computer Science 2021-09-14 Mehdi Arjmand , Mohammad Javad Dousti , Hadi Moradi

In deep learning, models typically reuse the same parameters for all inputs. Mixture of Experts (MoE) defies this and instead selects different parameters for each incoming example. The result is a sparsely-activated model -- with…

Machine Learning · Computer Science 2022-06-20 William Fedus , Barret Zoph , Noam Shazeer

Transformer-based pre-trained language models have proven to be effective for learning contextualized language representation. However, current approaches only take advantage of the output of the encoder's final layer when fine-tuning the…

Computation and Language · Computer Science 2020-04-30 Junjie Yang , Hai Zhao

We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance.…

Machine Learning · Computer Science 2026-02-04 Zishi Zhang , Jinhui Han , Ming Hu , Yijie Peng

The Transformer model, initially achieving significant success in the field of natural language processing, has recently shown great potential in the application of tactile perception. This review aims to comprehensively outline the…

Machine Learning · Computer Science 2024-05-22 Jing Gao , Ning Cheng , Bin Fang , Wenjuan Han

Background: Dedicated model transformation languages are claimed to provide many benefits over the use of general purpose languages for developing model transformations. However, the actual advantages and disadvantages associated with the…

Software Engineering · Computer Science 2022-09-15 Stefan Höppner , Matthias Tichy

Transformer models have recently achieved impressive performance on NLP tasks, owing to new algorithms for self-supervised pre-training on very large text corpora. In contrast, recent literature suggests that simple average word models…

Computer Vision and Pattern Recognition · Computer Science 2020-05-19 Muhammet Bastan , Arnau Ramisa , Mehmet Tek

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Huimin Huang , Shiao Xie1 , Lanfen Lin , Yutaro Iwamoto , Xianhua Han , Yen-Wei Chen , Ruofeng Tong
‹ Prev 1 3 4 5 6 7 10 Next ›