scholarly journals Group-wise Deep Co-saliency Detection

2017 ◽  
Author(s):  
Lina Wei ◽  
Shanshan Zhao ◽  
Omar El Farouk Bourahla ◽  
Xi Li ◽  
Fei Wu
Keyword(s):  
Collaborative Learning ◽  
Saliency Detection ◽  
Representation Learning ◽  
Feature Representation ◽  
Convolutional Network ◽  
Learning Framework ◽  
Detection Approach ◽  
End To End ◽  
Set Up ◽  
End Group

In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output. The proposed approach captures the group-wise interaction information for group images by learning a semantics-aware image representation based on a convolutional neural network, which adaptively learns the group-wise features for co-saliency detection. Furthermore, the proposed approach discovers the collaborative and interactive relationships between group-wise feature representation and single-image individual feature representation, and model this in a collaborative learning framework. Finally, we set up a unified end-to-end deep learning scheme to jointly optimize the process of group-wise feature representation learning and the collaborative learning, leading to more reliable and robust co-saliency detection results. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.

scholarly journals Multipath Cross Graph Convolution for Knowledge Representation Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Luogeng Tian ◽  
Bailong Yang ◽  
Xinli Yin ◽  
Kai Kang ◽  
Jing Wu
Keyword(s):  
Representation Learning ◽  
Knowledge Graph ◽  
Baseline Model ◽  
Convolutional Network ◽  
Redundant Feature ◽  
Feature Information ◽  
Semantic Spaces ◽  
Local Graph ◽  
End To End ◽  
Representation Method

In the past, most of the entity prediction methods based on embedding lacked the training of local core relationships, resulting in a deficiency in the end-to-end training. Aiming at this problem, we propose an end-to-end knowledge graph embedding representation method. It involves local graph convolution and global cross learning in this paper, which is called the TransC graph convolutional network (TransC-GCN). Firstly, multiple local semantic spaces are divided according to the largest neighbor. Secondly, a translation model is used to map the local entities and relationships into a cross vector, which serves as the input of GCN. Thirdly, through training and learning of local semantic relations, the best entities and strongest relations are found. The optimal entity relation combination ranking is obtained by evaluating the posterior loss function based on the mutual information entropy. Experiments show that this paper can obtain local entity feature information more accurately through the convolution operation of the lightweight convolutional neural network. Also, the maximum pooling operation helps to grasp the strong signal on the local feature, thereby avoiding the globally redundant feature. Compared with the mainstream triad prediction baseline model, the proposed algorithm can effectively reduce the computational complexity while achieving strong robustness. It also increases the inference accuracy of entities and relations by 8.1% and 4.4%, respectively. In short, this new method can not only effectively extract the local nodes and relationship features of the knowledge graph but also satisfy the requirements of multilayer penetration and relationship derivation of a knowledge graph.

LkeRec: Toward Lightweight End-to-End Joint Representation Learning for Building Accurate and Effective Recommendation

2022 ◽  
Vol 40 (3) ◽  
pp. 1-28
Author(s):  
Surong Yan ◽  
Kwei-Jay Lin ◽  
Xiaolin Zheng ◽  
Haosen Wang
Keyword(s):  
Side Information ◽  
Dimensional Space ◽  
Representation Learning ◽  
Knowledge Graph ◽  
Learning Framework ◽  
Relation Type ◽  
End To End ◽  
Low Dimensional ◽  
Item Knowledge ◽  
Explicit And Implicit Knowledge

Explicit and implicit knowledge about users and items have been used to describe complex and heterogeneous side information for recommender systems (RSs). Many existing methods use knowledge graph embedding (KGE) to learn the representation of a user-item knowledge graph (KG) in low-dimensional space. In this article, we propose a lightweight end-to-end joint learning framework for fusing the tasks of KGE and RSs at the model level. Our method proposes a lightweight KG embedding method by using bidirectional bijection relation-type modeling to enable scalability for large graphs while using self-adaptive negative sampling to optimize negative sample generating. Our method further generates the integrated views for users and items based on relation-types to explicitly model users’ preferences and items’ features, respectively. Finally, we add virtual “recommendation” relations between the integrated views of users and items to model the preferences of users on items, seamlessly integrating RS with user-item KG over a unified graph. Experimental results on multiple datasets and benchmarks show that our method can achieve a better accuracy of recommendation compared with existing state-of-the-art methods. Complexity and runtime analysis suggests that our method can gain a lower time and space complexity than most of existing methods and improve scalability.

Dilemma between constructivism and constructionism

2018 ◽  
Vol 11 (2) ◽  
pp. 273-290 ◽  
Author(s):  
Mohammad Rob ◽  
Farhana Rob
Keyword(s):  
Collaborative Learning ◽  
Learning Environment ◽  
Student Assessment ◽  
University Education ◽  
Learning Theories ◽  
Background Information ◽  
Content Type ◽  
Learning Framework ◽  
Set Up ◽  
Teaching Learning

Purpose This paper aims to provide a review of the two often-confusing learning theories: constructivism and constructionism. It then presents their similarities and differences by identifying various learning dimensions of the two philosophies. The authors then develop a teaching-learning framework that integrates those dimensions. The authors have also implemented the framework in two information technology (IT) courses and obtained students’ feedback that relate to various learning dimensions of both of the two philosophies. Design/methodology/approach The authors review existing literature to understand the difference between constructivism and constructionism and develop a list of learning dimensions that can be applied to classroom education. They then discuss the background information or tools necessary to develop a teaching-learning framework and apply that framework through a case study. They finally present the results. Findings A constructivist teacher sets up the learning environment for students that fosters individual learning and presents a problem to be solved, while the students go on their own way to produce a personally meaningful artifact without any further teacher’s intervention. On the other hand, the constructionist teacher sets up the environment for collaborative learning for students, then he or she defines the problem to be solved and the meaningful end product to be developed, and then guides them to reach towards the goal. Student assessment supports this difference. Research/limitations implications Researchers and teachers should look carefully which methodology they are discussing and which one they are applying. They can further the authors’ research in a different angle than the authors did by finding the learning dimensions. Practical implications Teachers should use constructionist approach to set up their classroom and guide their students throughout the course time, such that students can work collaboratively on a project to learn the important concepts to be developed. They should also use appropriate tools and technologies that enhance classroom activities and learning. Teacher should act as a guide/facilitator or a project manager to plan for the classroom/project and monitoring and controlling project/class throughout the semester. Social implications Understanding the critical differences between the two learning philosophies, educators in all levels should be clear how to set up their classrooms – from kindergarten to university education, such that all students can develop their knowledge not only through personal cognition but also through interaction with others. A collaborative environment produces knowledgeable people in the society with better understanding and respect toward each other. Originality/value Collaborative learning environment provides a better learning opportunity over personal cognition – a major enhancement in constructionism over constructivism. Sharing the creation process as well as the product, and the use of various tools and technologies in the development process, provide a better understanding of a subject matter. The discussions and results presented here might bring some insights to the instructors who might be contemplating to implement the educational philosophies of constructivism or constructionism, or intermixing of the two in their classrooms.

scholarly journals Enhancing interactive graph representation learning for review-based item recommendation

2021 ◽  
pp. 64-64
Author(s):  
Guojiang Shen ◽  
Jiajia Tan ◽  
Zhi Liu ◽  
Xiangjie Kong
Keyword(s):  
Dimensional Space ◽  
Representation Learning ◽  
User Preferences ◽  
Feature Representation ◽  
Graph Representation ◽  
High Dimensional ◽  
Convolutional Network ◽  
Latent Features ◽  
Rating Prediction ◽  
Real World Datasets

Collaborative filtering has been successful in the recommendation systems of various scenarios, but it is also hampered by issues such as cold start and data sparsity. To alleviate the above problems, recent studies have attempted to integrate review information into models to improve accuracy of rating prediction. While most of the existing models respectively utilize independent module to ex tract the latent feature representation of user reviews and item reviews, ignoring the correlation between the latent features, which may fail to capture the similarity of user preferences and item attributes hidden in different review text. On the other hand, the graph neural network can realize the information interaction in high dimensional space through deep architecture, which has been extensively studied in many fields. Therefore, in order to explore the high dimensional relevance between users and items hidden in the review information, we propose a new recommendation model enhancing interactive graph representation learning for review-based item recommendation, named IGRec. Specifically, we construct the user-review21 item graph with users/items as nodes and reviews as edges. We further add the connection of the user-user and the item-item to the graph by meta-path of user-item user and item-user-item. Then we utilize the attention mechanism to fuse edges information into nodes and apply the multilayer graph convolutional network to learn the high-order interactive information of nodes. Finally, we obtain the final embedding of user/item and adopt the factorization machine to complete the rating prediction. Experiments on the five real-world datasets demonstrate that the pro posed IGRec outperforms the state-of-the-art baselines.

scholarly journals A Novel Data Analytics Oriented Approach for Image Representation Learning in Manufacturing Systems

2022 ◽  
Vol 2022 ◽  
pp. 1-14
Author(s):  
Yue Liu ◽  
Junqi Ma ◽  
Xingzhen Tao ◽  
Jingyun Liao ◽  
Tao Wang ◽  
...  
Keyword(s):  
Manufacturing Systems ◽  
Image Representation ◽  
Image Data ◽  
Representation Learning ◽  
Hybrid Architecture ◽  
Convolutional Network ◽  
Learning Framework ◽  
Learning Tasks ◽  
Supervised Methods ◽  
Learned Features

In the era of digital manufacturing, huge amount of image data generated by manufacturing systems cannot be instantly handled to obtain valuable information due to the limitations (e.g., time) of traditional techniques of image processing. In this paper, we propose a novel self-supervised self-attention learning framework—TriLFrame for image representation learning. The TriLFrame is based on the hybrid architecture of Convolutional Network and Transformer. Experiments show that TriLFrame outperforms state-of-the-art self-supervised methods on the ImageNet dataset and achieves competitive performances when transferring learned features on ImageNet to other classification tasks. Moreover, TriLFrame verifies the proposed hybrid architecture, which combines the powerful local convolutional operation and the long-range nonlocal self-attention operation and works effectively in image representation learning tasks.

scholarly journals Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6975
Author(s):  
Tao Zhang ◽  
Lun He ◽  
Xudong Li ◽  
Guoqing Feng
Keyword(s):  
Performance Improvement ◽  
State Of The Art ◽  
Error Rates ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Sentence Level ◽  
End To End ◽  
High Level ◽  
Improved Accuracy ◽  
Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

W-MMP2Vec: Topic-driven network embedding model for link prediction in content-based heterogeneous information network

2021 ◽  
Vol 25 (3) ◽  
pp. 711-738
Author(s):  
Phu Pham ◽  
Phuc Do
Keyword(s):  
Link Prediction ◽  
Representation Learning ◽  
Information Network ◽  
Network Embedding ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Learning Framework ◽  
Novel Approach ◽  
Proposed Model ◽  
Meta Path

Link prediction on heterogeneous information network (HIN) is considered as a challenge problem due to the complexity and diversity in types of nodes and links. Currently, there are remained challenges of meta-path-based link prediction in HIN. Previous works of link prediction in HIN via network embedding approach are mainly focused on exploiting features of node rather than existing relations in forms of meta-paths between nodes. In fact, predicting the existence of new links between non-linked nodes is absolutely inconvincible. Moreover, recent HIN-based embedding models also lack of thorough evaluations on the topic similarity between text-based nodes along given meta-paths. To tackle these challenges, in this paper, we proposed a novel approach of topic-driven multiple meta-path-based HIN representation learning framework, namely W-MMP2Vec. Our model leverages the quality of node representations by combining multiple meta-paths as well as calculating the topic similarity weight for each meta-path during the processes of network embedding learning in content-based HINs. To validate our approach, we apply W-TMP2Vec model in solving several link prediction tasks in both content-based and non-content-based HINs (DBLP, IMDB and BlogCatalog). The experimental outputs demonstrate the effectiveness of proposed model which outperforms recent state-of-the-art HIN representation learning models.

scholarly journals A Novel Method to Predict Drug-Target Interactions Based on Large-Scale Graph Representation Learning

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2111
Author(s):  
Bo-Wei Zhao ◽  
Zhu-Hong You ◽  
Lun Hu ◽  
Zhen-Hao Guo ◽  
Lei Wang ◽  
...  
Keyword(s):  
Drug Target ◽  
Large Scale ◽  
Computational Models ◽  
Structural Information ◽  
Characteristic Curve ◽  
Representation Learning ◽  
Graph Representation ◽  
Convolutional Network ◽  
Novel Method

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with the time-consuming and labor-intensive in vivo experimental methods, the computational models can provide high-quality DTI candidates in an instant. In this study, we propose a novel method called LGDTI to predict DTIs based on large-scale graph representation learning. LGDTI can capture the local and global structural information of the graph. Specifically, the first-order neighbor information of nodes can be aggregated by the graph convolutional network (GCN); on the other hand, the high-order neighbor information of nodes can be learned by the graph embedding method called DeepWalk. Finally, the two kinds of feature are fed into the random forest classifier to train and predict potential DTIs. The results show that our method obtained area under the receiver operating characteristic curve (AUROC) of 0.9455 and area under the precision-recall curve (AUPR) of 0.9491 under 5-fold cross-validation. Moreover, we compare the presented method with some existing state-of-the-art methods. These results imply that LGDTI can efficiently and robustly capture undiscovered DTIs. Moreover, the proposed model is expected to bring new inspiration and provide novel perspectives to relevant researchers.

Sign in / Sign up

Export Citation Format

Share Document