Hybrid attention mechanism for few‐shot relational learning of knowledge graphs

Ma, Ruixin; Li, Zeyang; Guo, Fang‐Qing; Zhao, Liang

doi:10.1049/cvi2.12066

Cited by 6 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, many problems cannot be divided into a single problem. Subdividing a problem into subproblems may cause information loss between the subproblems [9]. Figure 1 shows the structures of single-task and multi-task learning.…”

Section: Research On Multi-task Learning Urban Spatial Quality Attrib...mentioning

confidence: 99%

Semantic and Instance Segmentation in Coastal Urban Spatial Perception: A Multi-Task Learning Framework with an Attention Mechanism

Zhang,

Liu,

Kim

2024

Sustainability

View full text Add to dashboard Cite

With the continuous acceleration of urbanization, urban planning and design require more in-depth research and development. Street view images can express rich urban features and guide residents’ emotions toward a city, thereby providing the most intuitive reflection of their perception of the city’s spatial quality. However, current researchers mainly conduct research on urban spatial quality through subjective experiential judgment, which includes problems such as a high cost and a low judgment accuracy. In response to these problems, this study proposes a multi-task learning urban spatial attribute perception model that integrates an attention mechanism. Via this model, the existing attributes of urban street scenes are analyzed. Then, the model is improved by introducing semantic segmentation and instance segmentation to identify and match the qualities of the urban space. The experimental results show that the multi-task learning urban spatial attribute perception model with an integrated attention mechanism has prediction accuracies of 79.54%, 78.62%, 79.68%, 77.42%, 78.45%, and 76.98% for the urban spatial attributes of beauty, boredom, depression, liveliness, safety, and richness, respectively. The accuracy of the multi-task learning urban spatial scene feature image segmentation model with an integrated attention mechanism is 95.4, 94.8, 96.2, 92.1, and 96.7 for roads, walls, sky, vehicles, and buildings, respectively. The multi-task learning urban spatial scene feature image segmentation model with an integrated attention mechanism has a higher recognition accuracy for urban spatial buildings than other models. These research results indicate the model’s effectiveness in matching urban spatial quality with public perception.

show abstract

Section: Research On Multi-task Learning Urban Spatial Quality Attrib...mentioning

confidence: 99%

Semantic and Instance Segmentation in Coastal Urban Spatial Perception: A Multi-Task Learning Framework with an Attention Mechanism

Zhang,

Liu,

Kim

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…The existing work [32,33] has proved that constructing model modeling can improve the accuracy of actual prediction. HAF [8] has proved that a one-step neighborhood is helpful for entity prediction, but this framework does not consider the feature influence of the same relational attributes on the source entity under different training tasks. To address this issue, we design an adaptive weighted entity augmentation encoder.…”

Section: Entity-enhanced Encodermentioning

confidence: 99%

“…Q, K, and V represent the three-element Query, Key, and Value of the self-attention mechanism. Through the above process, this module can obtain the weighted implicit features of the entity's one-hop neighbors through the Transformer encoder, as shown in Equation (8).…”

Section: Entity-enhanced Encodermentioning

confidence: 99%

“…This method is the first to achieve knowledge graph reasoning on a single sample and achieves suitable results on public datasets. HAF [8] is an effective hybrid attention mechanism learning framework that acquires highly interpretable entity aggregation information through an attention module. Among them, the entity enhancement encoder learns the hidden features of entities in different scenarios, adjacent encoders update entity features to accommodate different training processes, and then use the matching processor to infer entities.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs

et al. 2022

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Few-shot knowledge graph reasoning is a research focus in the field of knowledge graph reasoning. At present, in order to expand the application scope of knowledge graphs, a large number of researchers are devoted to the study of the multi-shot knowledge graph model. However, as far as we know, the knowledge graph contains a large number of missing relations and entities, and there are not many reference examples at the time of training. In this paper, our goal is to be able to infer the correct entity given a few training instances, or even only one training instance is available. Therefore, we propose an adaptive attentional network for few-shot relational learning of knowledge graphs, extracting knowledge based on traditional embedding methods, using the Transformer mechanism and hierarchical attention mechanism to obtain hidden attributes of entities, and then using a noise checker to filter out unreasonable candidate entities. Our model produces large performance improvements on the NELL-One dataset.

show abstract

“…Relying on abundant annotated data, deep learning techniques [1][2][3] have achieved significant breakthroughs in computer vision [4,5] with their excellent ability to learn feature representations. However, in some applications, collecting such large scales of annotated training data is often laborious, expensive, or even impossible.…”

Section: Introductionmentioning

confidence: 99%

Redefining prior feature space via finetuning a triplet network for few‐shot learning

2022

IET Computer Vision

View full text Add to dashboard Cite

Few‐shot learning is to distinguish novel concepts with few annotated data, which has attracted much attention due to its requirement of limited training data for target classes. Recent few‐shot learning methods usually pretrain a feature extractor with images from the base set to boost the performance of few‐shot tasks and classify novel categories in this prior feature space. However, it is difficult for the pretrained feature extractor to extract accurate representations for novel categories, resulting in large amounts of overlapping areas between new classes. To address these issues, the prior feature space with a triplet network to learn a more discriminative space is refined, where features belonging to same class are pulled together and that from different classes are pushed apart. Specifically, the authors first follow recent paradigm of pretraining to obtain a prior feature space. Then, a triplet network with contrastive learning is trained to project the features from this space into a low‐dimensional one. The main difference lies in that the authors’ model is based on Maximum A Posteriori (MAP) and the triplet network with hallucinated features is finetuned from it to make them generalise well to novel categories. Finally, the authors conduct classification tasks in the finetuned space. The authors’ intuition is that the overlapping areas in novel categories can be separated by finetuning the triplet network pretrained on base set with contrastive learning. Experimental results on four few‐shot benchmarks show that it significantly outperforms the baseline methods, improves around 1.09% ∼ 13.09% than the best results in each dataset on both 1‐ and 5‐shot tasks.

show abstract

Hybrid attention mechanism for few‐shot relational learning of knowledge graphs

Cited by 6 publications

References 23 publications

Semantic and Instance Segmentation in Coastal Urban Spatial Perception: A Multi-Task Learning Framework with an Attention Mechanism

Semantic and Instance Segmentation in Coastal Urban Spatial Perception: A Multi-Task Learning Framework with an Attention Mechanism

Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs

Redefining prior feature space via finetuning a triplet network for few‐shot learning

Contact Info

Product

Resources

About