This book constitutes the refereed proceedings of the 19th International Conference on Advanced Data Mining and Applications, ADMA 2023, held in Shenyang, China, during August 21-23, 2023.
The 216 full papers included in this book were carefully reviewed and selected from 503 submissions. They were organized in topical sections as follows: Data mining foundations, Grand challenges of data mining, Parallel and distributed data mining algorithms, Mining on data streams, Graph mining and Spatial data mining.
Inhaltsverzeichnis
Pharmaceutical Data Analysis
. - Drug-target interaction prediction based on drug subgraph fingerprint extraction strategy and subgraph attention mechanism. - Soft Prompt Transfer for Zero-Shot and Few-Shot Learning in EHR Understanding. - Graph Convolution Synthetic Transformer for Chronic Kidney Disease Onset Prediction. - MTFL: Multi-task feature learning with joint correlation structure learning for Alzheimer s disease cognitive performance prediction. - Multi-Level Transformer for Cancer Outcome Prediction in Large-Scale Claims Data. - Individual Functional Network Abnormalities Mapping via Graph Representation-based Neural Architecture Search. - A novel application of a mutual information measure for analysing temporal changes in healthcare network graphs. - Drugs Resistance Analysis from Scarce Health Records via Multi-task Graph Representation. -
Text Classification
. - ParaNet:Parallel Networks with Pre-trained Models for Text Classification. - Open Text Classification Based on Dynamic Boundary Balance. - A Prompt Tuning Method for Chinese Medical Text Classification. - TabMentor: Detect Errors on Tabular Data with Noisy Labels. - Label-aware Hierarchical Contrastive Domain Adaptation for Cross-network Node Classification. - Semi-supervised classification based on Graph Convolution Encoder Representations from BERT. - Global Balanced Text Classification for Stable Disease Diagnosis. -
Graph
. - Dominance Maximization in Uncertain Graphs. - LAGCL: Towards Stable and Automated Graph Contrastive Learning. - Discriminative Graph-level Anomaly Detection via Dual-students-teacher Model. - Common-Truss-based Community Search on Multilayer Graphs. - Learning To Predict Shortest Path Distance. - Efficient Regular Path Query Evaluation with Structural Path Constraints. EnSpeciVAT: Enhanced SpeciVAT for Cluster Tendency Identification in Graphs. - Pessimistic Adversarially Regularized Learning for Graph Embedding. - M2HGCL: Multi-Scale Meta-Path Integrated Heterogeneous Graph Contrastive Learning.