scholarly journals Effects of Nonlinear Functions on Knowledge Graph Convolutional Networks for Recommender Systems with Yelp Knowledge Graph

2021 ◽  
Author(s):  
Xing Wei ◽  
Jiangjiang Liu
Keyword(s):  
Recommender Systems ◽  
Sparse Data ◽  
Knowledge Graph ◽  
Order Structure ◽  
High Order Structure ◽  
Nonlinear Functions ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Processing Data ◽  
Knowledge Graphs

Knowledge Graph (KG) related recommendation method is advanced in dealing with cold start problems and sparse data. Knowledge Graph Convolutional Network (KGCN) is an end-to-end framework that has been proved to have the ability to capture latent item-entity features by mining their associated attributes on the KG. In KGCN, aggregator plays a key role for extracting information from the high-order structure. In this work, we proposed Knowledge Graph Processor (KGP) for pre-processing data and building corresponding knowledge graphs. A knowledge graph for the Yelp Open dataset was constructed with KGP. In addition, we investigated the impacts of various aggregators with three nonlinear functions on KGCN with Yelp Open dataset KG.

scholarly journals I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs

2019 ◽  
Vol 33 ◽  
pp. 8303-8311 ◽  
Author(s):  
Junyu Gao ◽  
Tianzhu Zhang ◽  
Changsheng Xu
Keyword(s):  
Action Recognition ◽  
Visual Cues ◽  
Feature Space ◽  
Experimental Results ◽  
Knowledge Graph ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Semantic Embedding ◽  
Structured Knowledge ◽  
Knowledge Graphs

Recently, with the ever-growing action categories, zero-shot action recognition (ZSAR) has been achieved by automatically mining the underlying concepts (e.g., actions, attributes) in videos. However, most existing methods only exploit the visual cues of these concepts but ignore external knowledge information for modeling explicit relationships between them. In fact, humans have remarkable ability to transfer knowledge learned from familiar classes to recognize unfamiliar classes. To narrow the knowledge gap between existing methods and humans, we propose an end-to-end ZSAR framework based on a structured knowledge graph, which can jointly model the relationships between action-attribute, action-action, and attribute-attribute. To effectively leverage the knowledge graph, we design a novel Two-Stream Graph Convolutional Network (TS-GCN) consisting of a classifier branch and an instance branch. Specifically, the classifier branch takes the semantic-embedding vectors of all the concepts as input, then generates the classifiers for action categories. The instance branch maps the attribute embeddings and scores of each video instance into an attribute-feature space. Finally, the generated classifiers are evaluated on the attribute features of each video, and a classification loss is adopted for optimizing the whole network. In addition, a self-attention module is utilized to model the temporal information of videos. Extensive experimental results on three realistic action benchmarks Olympic Sports, HMDB51 and UCF101 demonstrate the favorable performance of our proposed framework.

scholarly journals MOVIE RECOMMENDATION USING KNOWLEDGE GRAPH

2020 ◽  
pp. 99-103
Author(s):  
Navin Tatyaba Gopal ◽  
Anish Raj Khobragade
Keyword(s):  
Neural Network ◽  
Recommender Systems ◽  
Weighted Graph ◽  
Cold Start ◽  
Structured Data ◽  
Label Propagation ◽  
Knowledge Graph ◽  
Movie Recommendation ◽  
Knowledge Graphs ◽  
Prior Application

The Knowledge graphs (KGs) catches structured data and relationships among a bunch of entities and items. Generally, constitute an attractive origin of information that can advance the recommender systems. But, present methodologies of this area depend on manual element thus don’t permit for start to end training. This article proposes, Knowledge Graph along with Label Smoothness (KG-LS) to offer better suggestions for the recommender Systems. Our methodology processes user-specific entities by prior application of a function capability that recognizes key KG-relationships for a specific user. In this manner, we change the KG in a specific-user weighted graph followed by application of a graph neural network to process customized entity embedding. To give better preliminary predisposition, label smoothness comes into picture, which places items in the KG which probably going to have identical user significant names/scores. Use of, label smoothness gives regularization above the edge weights thus; we demonstrate that it is comparable to a label propagation plan on the graph. Additionally building-up a productive usage that symbolizes solid adaptability concerning the size of knowledge graph. Experimentation on 4 datasets shows that our strategy beats best in class baselines. This process likewise accomplishes solid execution in cold start situations where user-entity communications remain meager.

scholarly journals End-to-End Structure-Aware Convolutional Networks for Knowledge Base Completion

2019 ◽  
Vol 33 ◽  
pp. 3060-3067 ◽  
Author(s):  
Chao Shang ◽  
Yun Tang ◽  
Jing Huang ◽  
Jinbo Bi ◽  
Xiaodong He ◽  
...  
Keyword(s):  
Knowledge Base ◽  
State Of The Art ◽  
The State ◽  
Graph Connectivity ◽  
Knowledge Graph ◽  
Graph Node ◽  
Convolutional Network ◽  
Node Attributes ◽  
Knowledge Graphs ◽  
End To End

Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the current state-of-the-art ConvE. ConvE uses 2D convolution over embeddings and multiple layers of nonlinear features to model knowledge graphs. The model can be efficiently trained and scalable to large knowledge graphs. However, there is no structure enforcement in the embedding space of ConvE. The recent graph convolutional network (GCN) provides another way of learning graph node embedding by successfully utilizing graph connectivity structure. In this work, we propose a novel end-to-end StructureAware Convolutional Network (SACN) that takes the benefit of GCN and ConvE together. SACN consists of an encoder of a weighted graph convolutional network (WGCN), and a decoder of a convolutional network called Conv-TransE. WGCN utilizes knowledge graph node structure, node attributes and edge relation types. It has learnable weights that adapt the amount of information from neighbors used in local aggregation, leading to more accurate embeddings of graph nodes. Node attributes in the graph are represented as additional nodes in the WGCN. The decoder Conv-TransE enables the state-of-the-art ConvE to be translational between entities and relations while keeps the same link prediction performance as ConvE. We demonstrate the effectiveness of the proposed SACN on standard FB15k-237 and WN18RR datasets, and it gives about 10% relative improvement over the state-of-theart ConvE in terms of HITS@1, HITS@3 and HITS@10.

scholarly journals Discovering alignment relations with Graph Convolutional Networks: A biomedical case study

Semantic Web ◽  
2021 ◽  
pp. 1-20
Author(s):  
Pierre Monnin ◽  
Chedy Raïssi ◽  
Amedeo Napoli ◽  
Adrien Coulet
Keyword(s):  
Domain Knowledge ◽  
Knowledge Graph ◽  
Convolutional Networks ◽  
Real World Application ◽  
Web Of Data ◽  
Knowledge Graphs ◽  
The Web ◽  
Node Embeddings ◽  
Weak Similarity

Knowledge graphs are freely aggregated, published, and edited in the Web of data, and thus may overlap. Hence, a key task resides in aligning (or matching) their content. This task encompasses the identification, within an aggregated knowledge graph, of nodes that are equivalent, more specific, or weakly related. In this article, we propose to match nodes within a knowledge graph by (i) learning node embeddings with Graph Convolutional Networks such that similar nodes have low distances in the embedding space, and (ii) clustering nodes based on their embeddings, in order to suggest alignment relations between nodes of a same cluster. We conducted experiments with this approach on the real world application of aligning knowledge in the field of pharmacogenomics, which motivated our study. We particularly investigated the interplay between domain knowledge and GCN models with the two following focuses. First, we applied inference rules associated with domain knowledge, independently or combined, before learning node embeddings, and we measured the improvements in matching results. Second, while our GCN model is agnostic to the exact alignment relations (e.g., equivalence, weak similarity), we observed that distances in the embedding space are coherent with the “strength” of these different relations (e.g., smaller distances for equivalences), letting us considering clustering and distances in the embedding space as a means to suggest alignment relations in our case study.

scholarly journals Attention-Based Graph Convolutional Network for Zero-Shot Learning with Pre-Training

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Xuefei Wu ◽  
Mingjiang Liu ◽  
Bo Xin ◽  
Zhangqing Zhu ◽  
Gang Wang
Keyword(s):  
Loss Function ◽  
Attention Mechanism ◽  
Propagation Model ◽  
Knowledge Graph ◽  
Learning Paradigm ◽  
Convolutional Network ◽  
Dense Graph ◽  
Convolutional Networks ◽  
Central Node ◽  
Graph Propagation

Zero-shot learning (ZSL) is a powerful and promising learning paradigm for classifying instances that have not been seen in training. Although graph convolutional networks (GCNs) have recently shown great potential for the ZSL tasks, these models cannot adjust the constant connection weights between the nodes in knowledge graph and the neighbor nodes contribute equally to classify the central node. In this study, we apply an attention mechanism to adjust the connection weights adaptively to learn more important information for classifying unseen target nodes. First, we propose an attention graph convolutional network for zero-shot learning (AGCNZ) by integrating the attention mechanism and GCN directly. Then, in order to prevent the dilution of knowledge from distant nodes, we apply the dense graph propagation (DGP) model for the ZSL tasks and propose an attention dense graph propagation model for zero-shot learning (ADGPZ). Finally, we propose a modified loss function with a relaxation factor to further improve the performance of the learned classifier. Experimental results under different pre-training settings verified the effectiveness of the proposed attention-based models for ZSL.

End-to-end Relation-Enhanced Learnable Graph Self-attention Network for Knowledge Graphs Embedding

2021 ◽  
Author(s):  
Shengchen Jiang ◽  
Hongbin Wang ◽  
Xiang Hou
Keyword(s):  
Large Scale ◽  
Structural Characteristics ◽  
Graph Embedding ◽  
Knowledge Graph ◽  
Data Sets ◽  
Relevance Ranking ◽  
Convolutional Network ◽  
Attention Network ◽  
Knowledge Graphs ◽  
End To End

Abstract The existing methods ignore the adverse effect of knowledge graph incompleteness on knowledge graph embedding. In addition, the complexity and large-scale of knowledge information hinder knowledge graph embedding performance of the classic graph convolutional network. In this paper, we analyzed the structural characteristics of knowledge graph and the imbalance of knowledge information. Complex knowledge information requires that the model should have better learnability, rather than linearly weighted qualitative constraints, so the method of end-to-end relation-enhanced learnable graph self-attention network for knowledge graphs embedding is proposed. Firstly, we construct the relation-enhanced adjacency matrix to consider the incompleteness of the knowledge graph. Secondly, the graph self-attention network is employed to obtain the global encoding and relevance ranking of entity node information. Thirdly, we propose the concept of convolutional knowledge subgraph, it is constructed according to the entity relevance ranking. Finally, we improve the training effect of the convKB model by changing the construction of negative samples to obtain a better reliability score in the decoder. The experimental results based on the data sets FB15k-237 and WN18RR show that the proposed method facilitates more comprehensive representation of knowledge information than the existing methods, in terms of Hits@10 and MRR.

scholarly journals KGGCN: Knowledge-Guided Graph Convolutional Networks for Distantly Supervised Relation Extraction

2021 ◽  
Vol 11 (16) ◽  
pp. 7734
Author(s):  
Ningyi Mao ◽  
Wenti Huang ◽  
Hai Zhong
Keyword(s):  
Prior Knowledge ◽  
Structural Information ◽  
Relation Extraction ◽  
Attention Mechanism ◽  
Knowledge Graph ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Lexical Resource ◽  
Sentence Level ◽  
The Impact

Distantly supervised relation extraction is the most popular technique for identifying semantic relation between two entities. Most prior models only focus on the supervision information present in training sentences. In addition to training sentences, external lexical resource and knowledge graphs often contain other relevant prior knowledge. However, relation extraction models usually ignore such readily available information. Moreover, previous works only utilize a selective attention mechanism over sentences to alleviate the impact of noise, they lack the consideration of the implicit interaction between sentences with relation facts. In this paper, (1) a knowledge-guided graph convolutional network is proposed based on the word-level attention mechanism to encode the sentences. It can capture the key words and cue phrases to generate expressive sentence-level features by attending to the relation indicators obtained from the external lexical resource. (2) A knowledge-guided sentence selector is proposed, which explores the semantic and structural information of triples from knowledge graph as sentence-level knowledge attention to distinguish the importance of each individual sentence. Experimental results on two widely used datasets, NYT-FB and GDS, show that our approach is able to efficiently use the prior knowledge from the external lexical resource and knowledge graph to enhance the performance of distantly supervised relation extraction.

scholarly journals Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

2019 ◽  
Author(s):  
Yuting Wu ◽  
Xiao Liu ◽  
Yansong Feng ◽  
Zheng Wang ◽  
Rui Yan ◽  
...  
Keyword(s):  
Real World ◽  
State Of The Art ◽  
Dual Graph ◽  
Knowledge Graph ◽  
Convolutional Network ◽  
Complex Relation ◽  
Dual Relation ◽  
Knowledge Graphs ◽  
Cross Lingual ◽  
Heterogeneous Knowledge

Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.

Sign in / Sign up

Export Citation Format

Share Document