paper-with-me

홈 › Papers

AprilE: Attention with Pseudo Residual Connection for Knowledge Graph Embedding

2020-12-01 · COLING 2020 8 · Yuzhang Liu, Peng Wang, Yingtai Li, Yizhan Shao, Zhongkai Xu

Knowledge graph embedding maps entities and relations into low-dimensional vector space. However, it is still challenging for many existing methods to model diverse relational patterns, especially symmetric and antisymmetric relations. To address this issue, we propose a novel model, AprilE, which employs triple-level self-attention and pseudo residual connection to model relational patterns. The triple-level self-attention treats head entity, relation, and tail entity as a sequence and captures the dependency within a triple. At the same time the pseudo residual connection retains primitive semantic features. Furthermore, to deal with symmetric and antisymmetric relations, two schemas of score function are designed via a position-adaptive mechanism. Experimental results on public datasets demonstrate that our model can produce expressive knowledge embedding and significantly outperforms most of the state-of-the-art works.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Graph EmbeddingKnowledge Graph EmbeddingPosition

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation

2026-03-28 · Xinyu Liu, Qing Xu, Zhen Chen arxiv

In the field of Large Language Models (LLMs), Attention Residuals have recently demonstrated that learned, selective aggregation over all preceding layer outputs can outperform fixed residual connections. We propose Cros…

Medical Image Segmentation

RRA: Recurrent Residual Attention for Sequence Learning

2017-09-12 · Cheng Wang

In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data. We propose to add residual connections across timesteps to RNN, which explic…

Sentiment Analysis

Image Super-Resolution Using Very Deep Residual Channel Attention Networks

2018-07-08 · ECCV 2018 9 · Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang 외

Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The low-resolution inputs and features…

Image Super-ResolutionSuper-Resolution

A self-training framework for glaucoma grading in OCT B-scans

2021-11-23 · Gabriel García, Adrián Colomer, Rafael Verdú-Monedero, José Dolz 외

In this paper, we present a self-training-based framework for glaucoma grading using OCT B-scans under the presence of domain shift. Particularly, the proposed two-step learning methodology resorts to pseudo-labels gener…

A Dynamic Residual Self-Attention Network for Lightweight Single Image Super-Resolution

2021-12-08 · Karam Park, Jae Woong Soh, Nam Ik Cho

Deep learning methods have shown outstanding performance in many applications, including single-image super-resolution (SISR). With residual connection architecture, deeply stacked convolutional neural networks provide a…

Image Super-ResolutionSuper-Resolution