Título :	25th Pacific-Asia Conference, PAKDD 2021, Virtual Event, May 11–14, 2021, Proceedings, Part III
Tipo de documento:	documento electrónico
Autores:	Karlapalem, Kamal, ; Cheng, Hong, ; Ramakrishnan, Naren, ; Agrawal, R. K., ; Reddy, P. Krishna, ; Srivastava, Jaideep, ; Chakraborty, Tanmoy,
Mención de edición:	1 ed.
Editorial:	[s.l.] : Springer
Fecha de publicación:	2021
Número de páginas:	XXIII, 434 p. 142 ilustraciones, 117 ilustraciones en color.
ISBN/ISSN/DL:	978-3-030-75768-7
Nota general:	Libro disponible en la plataforma SpringerLink. Descarga y lectura en formatos PDF, HTML y ePub. Descarga completa o por capítulos.
Palabras clave:	Inteligencia artificial  Ciencias sociales  Algoritmos  Informática  Visión por computador  Aplicación informática en ciencias sociales y del comportamiento  Diseño y Análisis de Algoritmos  Computadoras y Educación  Matemáticas de la Computación
Índice Dewey:	006.3 Inteligencia artificial
Resumen:	El conjunto de tres volúmenes LNAI 12712-12714 constituye las actas de la 25.ª Conferencia de Asia Pacífico sobre avances en el descubrimiento de conocimientos y la minería de datos, PAKDD 2021, que se celebró del 11 al 14 de mayo de 2021. Los 157 artículos incluidos en las actas fueron cuidadosamente revisado y seleccionado de un total de 628 presentaciones. Se organizaron en secciones temáticas de la siguiente manera: Parte I: Aplicaciones del descubrimiento de conocimientos y extracción de datos especializados; Parte II: Minería de datos clásica; teoría y principios de minería de datos; sistemas de recomendación; y análisis de texto; Parte III: Aprendizaje e incorporación de representaciones, y aprendizaje a partir de datos.
Nota de contenido:	Representation Learning and Embedding -- Episode Adaptive Embedding Networks for Few-shot Learning -- Universal Representation for Code -- Self-supervised Adaptive Aggregator Learning on Graph -- A Fast Algorithm for Simultaneous Sparse Approximation -- STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning -- RW-GCN: Training Graph Convolution Networks with biased random walk for Semi-Supervised Classification -- Loss-aware Pattern Inference: A Correction on the Wrongly Claimed Limitations of Embedding Models -- SST-GNN: Simplified Spatio-temporal Traffic forecasting model using Graph Neural Network -- VIKING: Adversarial Attack on Network Embeddings via Supervised Network Poisoning -- Self-supervised Graph Representation Learning with Variational Inference -- Manifold Approximation and Projection by Maximizing Graph Information -- Learning Attention-based Translational Knowledge Graph Embedding via Nonlinear Dynamic Mapping -- Multi-Grained Dependency Graph Neural Network for Chinese Open Information Extraction -- Human-Understandable Decision Making for Visual Recognition -- LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding -- Transferring Domain Knowledge with an Adviser in Continuous Tasks -- Inferring Hierarchical Mixture Structures: A Bayesian Nonparametric Approach -- Quality Control for Hierarchical Classification with Incomplete Annotations -- Learning from Data -- Learning Discriminative Features using Multi-label Dual Space -- AutoCluster: Meta-learning Based Ensemble Method for Automated Unsupervised Clustering -- BanditRank: Learning to Rank Using Contextual Bandits -- A compressed and accelerated SegNet for plant leaf disease segmentation: A Differential Evolution based approach -- Meta-Context Transformers for Domain-Specific Response Generation -- A Multi-task Kernel Learning Algorithm for Survival Analysis -- Meta-data Augmentation based Search Strategy through Generative Adversarial Network for AutoML Model Selection -- Tree-Capsule: Tree-Structured Capsule Network for Improving Relation Extraction -- Rule Injection-based Generative Adversarial Imitation Learning for Knowledge Graph Reasoning -- Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition -- Reinforced Natural Language Inference for Distantly Supervised Relation Classification -- SaGCN: Structure-aware Graph Convolution Network for Document-level Relation Extraction -- Addressing the class imbalance problem in medical image segmentation via accelerated Tversky loss function -- Incorporating Relational Knowledge in Explainable Fake News Detection -- Incorporating Syntactic Information into Relation Representations for Enhanced Relation Extraction.
En línea:	https://link-springer-com.biblioproxy.umanizales.edu.co/referencework/10.1007/97 [...]
Link:	https://biblioteca.umanizales.edu.co/ils/opac_css/index.php?lvl=notice_display&i

25th Pacific-Asia Conference, PAKDD 2021, Virtual Event, May 11–14, 2021, Proceedings, Part III [documento electrónico] / Karlapalem, Kamal, ; Cheng, Hong, ; Ramakrishnan, Naren, ; Agrawal, R. K., ; Reddy, P. Krishna, ; Srivastava, Jaideep, ; Chakraborty, Tanmoy,  . -  1 ed.  . - [s.l.] : Springer, 2021 . - XXIII, 434 p. 142 ilustraciones, 117 ilustraciones en color.
ISBN : 978-3-030-75768-7
Libro disponible en la plataforma SpringerLink. Descarga y lectura en formatos PDF, HTML y ePub. Descarga completa o por capítulos.

Palabras clave:	Inteligencia artificial  Ciencias sociales  Algoritmos  Informática  Visión por computador  Aplicación informática en ciencias sociales y del comportamiento  Diseño y Análisis de Algoritmos  Computadoras y Educación  Matemáticas de la Computación
Índice Dewey:	006.3 Inteligencia artificial
Resumen:	El conjunto de tres volúmenes LNAI 12712-12714 constituye las actas de la 25.ª Conferencia de Asia Pacífico sobre avances en el descubrimiento de conocimientos y la minería de datos, PAKDD 2021, que se celebró del 11 al 14 de mayo de 2021. Los 157 artículos incluidos en las actas fueron cuidadosamente revisado y seleccionado de un total de 628 presentaciones. Se organizaron en secciones temáticas de la siguiente manera: Parte I: Aplicaciones del descubrimiento de conocimientos y extracción de datos especializados; Parte II: Minería de datos clásica; teoría y principios de minería de datos; sistemas de recomendación; y análisis de texto; Parte III: Aprendizaje e incorporación de representaciones, y aprendizaje a partir de datos.
Nota de contenido:	Representation Learning and Embedding -- Episode Adaptive Embedding Networks for Few-shot Learning -- Universal Representation for Code -- Self-supervised Adaptive Aggregator Learning on Graph -- A Fast Algorithm for Simultaneous Sparse Approximation -- STEPs-RL: Speech-Text Entanglement for Phonetically Sound Representation Learning -- RW-GCN: Training Graph Convolution Networks with biased random walk for Semi-Supervised Classification -- Loss-aware Pattern Inference: A Correction on the Wrongly Claimed Limitations of Embedding Models -- SST-GNN: Simplified Spatio-temporal Traffic forecasting model using Graph Neural Network -- VIKING: Adversarial Attack on Network Embeddings via Supervised Network Poisoning -- Self-supervised Graph Representation Learning with Variational Inference -- Manifold Approximation and Projection by Maximizing Graph Information -- Learning Attention-based Translational Knowledge Graph Embedding via Nonlinear Dynamic Mapping -- Multi-Grained Dependency Graph Neural Network for Chinese Open Information Extraction -- Human-Understandable Decision Making for Visual Recognition -- LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding -- Transferring Domain Knowledge with an Adviser in Continuous Tasks -- Inferring Hierarchical Mixture Structures: A Bayesian Nonparametric Approach -- Quality Control for Hierarchical Classification with Incomplete Annotations -- Learning from Data -- Learning Discriminative Features using Multi-label Dual Space -- AutoCluster: Meta-learning Based Ensemble Method for Automated Unsupervised Clustering -- BanditRank: Learning to Rank Using Contextual Bandits -- A compressed and accelerated SegNet for plant leaf disease segmentation: A Differential Evolution based approach -- Meta-Context Transformers for Domain-Specific Response Generation -- A Multi-task Kernel Learning Algorithm for Survival Analysis -- Meta-data Augmentation based Search Strategy through Generative Adversarial Network for AutoML Model Selection -- Tree-Capsule: Tree-Structured Capsule Network for Improving Relation Extraction -- Rule Injection-based Generative Adversarial Imitation Learning for Knowledge Graph Reasoning -- Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition -- Reinforced Natural Language Inference for Distantly Supervised Relation Classification -- SaGCN: Structure-aware Graph Convolution Network for Document-level Relation Extraction -- Addressing the class imbalance problem in medical image segmentation via accelerated Tversky loss function -- Incorporating Relational Knowledge in Explainable Fake News Detection -- Incorporating Syntactic Information into Relation Representations for Enhanced Relation Extraction.
En línea:	https://link-springer-com.biblioproxy.umanizales.edu.co/referencework/10.1007/97 [...]
Link:	https://biblioteca.umanizales.edu.co/ils/opac_css/index.php?lvl=notice_display&i