English
Related papers

Related papers: Directed Acyclic Transformer for Non-Autoregressiv…

200 papers

Recent advances in text recognition led to a paradigm shift for page-level recognition, from multi-step segmentation-based approaches to end-to-end attention-based ones. However, the na\"ive character-level autoregressive decoding process…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Denis Coquenet

Knowledge distillation (KD) is essential for training non-autoregressive translation (NAT) models by reducing the complexity of the raw data with an autoregressive teacher model. In this study, we empirically show that as a side effect of…

Computation and Language · Computer Science 2021-01-28 Liang Ding , Longyue Wang , Xuebo Liu , Derek F. Wong , Dacheng Tao , Zhaopeng Tu

State-of-the-art sequence-to-sequence models often require autoregressive decoding, which can be highly expensive. However, for some downstream tasks such as out-of-distribution (OOD) detection and resource allocation, the actual decoding…

Machine Learning · Computer Science 2023-05-10 Yassir Fathullah , Puria Radmard , Adian Liusie , Mark J. F. Gales

Transformers have revolutionized performance in Natural Language Processing and Vision, paving the way for their integration with Graph Neural Networks (GNNs). One key challenge in enhancing graph transformers is strengthening the…

Machine Learning · Computer Science 2026-01-09 Yun Young Choi , Sun Woo Park , Minho Lee , Youngho Woo

Causal models in statistics are often described using acyclic directed mixed graphs (ADMGs), which contain directed and bidirected edges and no directed cycles. This article surveys various interpretations of ADMGs, discusses their…

Statistics Theory · Mathematics 2025-03-28 Qingyuan Zhao

With the rapid advancement of Transformer-based Large Language Models (LLMs), generative recommendation has shown great potential in enhancing both the accuracy and semantic understanding of modern recommender systems. Compared to LLMs, the…

Information Retrieval · Computer Science 2025-08-19 Xiang Gao , Tianyuan Liu , Yisha Li , Jingxin Liu , Lexi Gao , Xin Li , Haiyang Lu , Liyin Hong

Graphs are the natural data structure to represent relational and structural information in many domains. To cover the broad range of graph-data applications including graph classification as well as graph generation, it is desirable to…

Machine Learning · Computer Science 2020-06-11 Sanghyun Yoo , Young-Seok Kim , Kang Hyun Lee , Kuhwan Jeong , Junhwi Choi , Hoshik Lee , Young Sang Choi

Autoregressive sequence Generation models have achieved state-of-the-art performance in areas like machine translation and image captioning. These models are autoregressive in that they generate each word by conditioning on previously…

Computation and Language · Computer Science 2021-01-26 Longteng Guo , Jing Liu , Xinxin Zhu , Hanqing Lu

Directed Acyclic Graph (DAG) is a popular approach to achieve scalability of blockchain networks. Due to its high efficiency in data communication and great scalability, DAG has been widely adopted in many applications such as Internet of…

Networking and Internet Architecture · Computer Science 2022-07-12 Canhui Chen , Xu Chen , Zhixuan Fang

In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks,…

Computation and Language · Computer Science 2018-08-01 Hasan Sait Arslan , Mark Fishel , Gholamreza Anbarjafari

Transformers have achieved great success in several domains, including Natural Language Processing and Computer Vision. However, its application to real-world graphs is less explored, mainly due to its high computation cost and its poor…

Machine Learning · Computer Science 2023-01-31 Weilin Cong , Yanhong Wu , Yuandong Tian , Mengting Gu , Yinglong Xia , Chun-cheng Jason Chen , Mehrdad Mahdavi

The Transformer architecture is widely used for machine translation tasks. However, its resource-intensive nature makes it challenging to implement on constrained embedded devices, particularly where available hardware resources can vary at…

Computation and Language · Computer Science 2021-08-03 Hishan Parry , Lei Xun , Amin Sabet , Jia Bi , Jonathon Hare , Geoff V. Merrett

Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs. While architectural advances such as the Transformer fully parallelize the…

Computation and Language · Computer Science 2020-10-06 Nader Akoury , Kalpesh Krishna , Mohit Iyyer

Graph Attention Network (GAT) is one of the most popular Graph Neural Network (GNN) architecture, which employs the attention mechanism to learn edge weights and has demonstrated promising performance in various applications. However, since…

Machine Learning · Computer Science 2024-03-05 Qincheng Lu , Jiaqi Zhu , Sitao Luan , Xiao-Wen Chang

A directed acyclic graph (DAG) provides valuable prior knowledge that is often discarded in regression tasks in machine learning. We show that the independences arising from the presence of collider structures in DAGs provide meaningful…

Machine Learning · Statistics 2023-06-22 Shahine Bouabid , Jake Fawkes , Dino Sejdinovic

Non-autoregressive translation (NAT) model achieves a much faster inference speed than the autoregressive translation (AT) model because it can simultaneously predict all tokens during inference. However, its translation quality suffers…

Computation and Language · Computer Science 2023-01-30 Huanran Zheng , Wei Zhu , Pengfei Wang , Xiaoling Wang

Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their…

Computation and Language · Computer Science 2022-10-24 Robin M. Schmidt , Telmo Pires , Stephan Peitz , Jonas Lööf

Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. However, they are difficult to parallelize and are thus slow at processing long…

Machine Learning · Computer Science 2018-06-11 Łukasz Kaiser , Aurko Roy , Ashish Vaswani , Niki Parmar , Samy Bengio , Jakob Uszkoreit , Noam Shazeer

Transfer learning is a crucial technique for handling a small amount of data that is potentially related to other abundant data. However, most of the existing methods are focused on classification tasks using images and language datasets.…

Artificial Intelligence · Computer Science 2025-06-16 Sung Moon Ko , Sumin Lee , Dae-Woong Jeong , Woohyung Lim , Sehui Han

With huge amounts of training data, deep learning has made great breakthroughs in many artificial intelligence (AI) applications. However, such large-scale data sets present computational challenges, requiring training to be distributed on…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-11-01 Shaohuai Shi , Qiang Wang , Xiaowen Chu , Bo Li