Bernnet: Learning arbitrary graph spectral filters via bernstein approximation
Many representative graph neural networks, $ eg $, GPR-GNN and ChebNet, approximate
graph convolutions with graph spectral filters. However, existing work either applies …
graph convolutions with graph spectral filters. However, existing work either applies …
Convolutional neural networks on graphs with chebyshev approximation, revisited
Designing spectral convolutional networks is a challenging problem in graph learning.
ChebNet, one of the early attempts, approximates the spectral graph convolutions using …
ChebNet, one of the early attempts, approximates the spectral graph convolutions using …
Scalable graph neural networks via bidirectional propagation
Abstract Graph Neural Networks (GNN) are an emerging field for learning on non-Euclidean
data. Recently, there has been increased interest in designing GNN that scales to large …
data. Recently, there has been increased interest in designing GNN that scales to large …
A survey on legal question–answering systems
J Martinez-Gil - Computer Science Review, 2023 - Elsevier
Many legal professionals think the explosion of information about local, regional, national,
and international legislation makes their practice more costly, time-consuming, and error …
and international legislation makes their practice more costly, time-consuming, and error …
[PDF][PDF] BERT-INT: A BERT-based interaction model for knowledge graph alignment
Abstract Knowledge graph alignment aims to link equivalent entities across different
knowledge graphs. To utilize both the graph structures and the side information such as …
knowledge graphs. To utilize both the graph structures and the side information such as …
GCN: Graph Gaussian Convolution Networks with Concentrated Graph Filters
Recently, linear GCNs have shown competitive performance against non-linear ones with
less computation cost, and the key lies in their propagation layers. Spectral analysis has …
less computation cost, and the key lies in their propagation layers. Spectral analysis has …
[HTML][HTML] A hereditary attentive template-based approach for complex knowledge base question answering systems
J Gomes Jr, RC de Mello, V Ströele… - Expert Systems with …, 2022 - Elsevier
Abstract Knowledge Base Question Answering systems (KBQA) aim to find answers to
natural language questions over a knowledge base. This work presents a template matching …
natural language questions over a knowledge base. This work presents a template matching …
A study of approaches to answering complex questions over knowledge bases
J Gomes Jr, RC de Mello, V Ströele… - … and Information Systems, 2022 - Springer
Question answering (QA) systems retrieve the most relevant answer to a natural language
question. Knowledge base question answering (KBQA) systems explore entities and …
question. Knowledge base question answering (KBQA) systems explore entities and …
A two-phase prototypical network model for incremental few-shot relation classification
Relation Classification (RC) plays an important role in natural language processing (NLP).
Current conventional supervised and distantly supervised RC models always make a closed …
Current conventional supervised and distantly supervised RC models always make a closed …
Make it easy: An effective end-to-end entity alignment framework
Entity alignment (EA) is a prerequisite for enlarging the coverage of a unified knowledge
graph. Previous EA approaches either restrain the performance due to inadequate …
graph. Previous EA approaches either restrain the performance due to inadequate …