| |
|
|
|
|
|
|
|
|
1. |
Record Nr. |
UNINA9910886078403321 |
|
|
Autore |
Onizuka Makoto |
|
|
Titolo |
Database Systems for Advanced Applications : 29th International Conference, DASFAA 2024, Gifu, Japan, July 2–5, 2024, Proceedings, Part VI / / edited by Makoto Onizuka, Jae-Gil Lee, Yongxin Tong, Chuan Xiao, Yoshiharu Ishikawa, Sihem Amer-Yahia, H. V. Jagadish, Kejing Lu |
|
|
|
|
|
|
|
Pubbl/distr/stampa |
|
|
Singapore : , : Springer Nature Singapore : , : Imprint : Springer, , 2024 |
|
|
|
|
|
|
|
ISBN |
|
|
|
|
|
|
Edizione |
[1st ed. 2024.] |
|
|
|
|
|
Descrizione fisica |
|
1 online resource (510 pages) |
|
|
|
|
|
|
Collana |
|
Lecture Notes in Computer Science, , 1611-3349 ; ; 14855 |
|
|
|
|
|
|
Altri autori (Persone) |
|
LeeJae-Gil |
TongYongxin |
XiaoChuan |
IshikawaYoshiharu |
Amer-YahiaSihem |
JagadishH. V |
LuKejing |
|
|
|
|
|
|
|
|
Disciplina |
|
|
|
|
|
|
Soggetti |
|
Machine learning |
Application software |
Computers |
Computer networks |
Computers, Special purpose |
Machine Learning |
Computer and Information Systems Applications |
Computing Milieux |
Computer Communication Networks |
Special Purpose and Application-Based Systems |
|
|
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
Nota di contenuto |
|
Intro -- Preface -- Organization -- Contents - Part VI -- Graph and Network -- Cascading Graph Convolution Contrastive Learning Networks for Multi-behavior Recommendation -- 1 Introduction -- 2 Related Work -- 3 Problem Definition -- 4 Proposed Model -- 4.1 |
|
|
|
|
|
|
|
|
|
Overall Framework -- 4.2 Node Representation Learning -- 4.3 Multi-task Learning -- 4.4 Contrastive Learning -- 4.5 Joint Optimization -- 5 Experiment -- 5.1 Experiment Settings -- 5.2 Overall Performance -- 5.3 Ablation Study -- 5.4 Hyper-parameter Study -- 6 Conclusion -- References -- Social Relation Enhanced Heterogeneous Graph Contrastive Learning for Recommendation -- 1 Introduction -- 2 Related Work -- 2.1 Social Recommendation -- 2.2 Heterogeneous Graph Learning -- 2.3 Contrastive Learning for Recommendation -- 3 Methodology -- 3.1 Definitions and Problem Formulation -- 3.2 Cross-View Heterogeneous Graph Construction -- 3.3 View-Based Graph Learning -- 3.4 View-Level Contrastive Learning -- 3.5 Multi-task Training -- 4 Experiment -- 4.1 Experimental Setting -- 4.2 Performance Comparision(RQ1) -- 4.3 Experiment with Effectiveness(RQ2) -- 4.4 Hyper-parameter Analysis(RQ3) -- 5 Conclusion -- References -- Higher-Order Graph Contrastive Learning for Recommendation -- 1 Introduction -- 2 Preliminaries -- 3 The Proposed Method -- 3.1 Construction of High-Order Graphs -- 3.2 Message Propagation and Knowledge Fusion -- 3.3 Contrastive Learning for High-Order View -- 3.4 Contrastive Learning for General View -- 3.5 Optimization -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Overall Performance Comparison -- 4.3 Further Analysis of HoGCL -- 5 Related Work -- 6 Conclusion -- References -- FNDPro: Evaluating the Importance of Propagations during Fake News Spread -- 1 Introduction -- 2 Related Work -- 2.1 Content-Based Models -- 2.2 Graph-Based Models -- 3 Methodology. |
3.1 News Propagation Network -- 3.2 Propagation Encoder -- 3.3 Propagation Transformer Module -- 3.4 Learning and Optimization -- 4 Experiments -- 4.1 Main Results -- 4.2 Propagation Transformer Study -- 4.3 Discussion -- 4.4 Case Study -- 5 Conclusion -- References -- Leveraging Homophily-Augmented Energy Propagation for Bot Detection on Graphs -- 1 Introduction -- 2 Preliminaries and Problem Statement -- 3 Proposed Model -- 3.1 Impacts of Graph Structure on In-Distribution Learning -- 3.2 Heterophily-Wise Node Embedding Learning -- 3.3 Energy Calculation -- 3.4 Homophily-Augmented Energy Propagation -- 3.5 Loss Function -- 4 Experimental Results and Analysis -- 4.1 Experimental Setup -- 4.2 Effectiveness of Edge Prediction -- 4.3 Comparison with Baselines for Bot Detection -- 4.4 Case Study: ODD for Bot Detection -- 4.5 Ablation Study -- 5 Conclusion -- References -- Multi-level Contrastive Learning on Weak Social Networks for Information Diffusion Prediction -- 1 Introduction -- 2 Preliminaries -- 3 Methodology -- 3.1 Multiplex Heterogeneous Graph Learning -- 3.2 Self-supervised Graph Training -- 3.3 Information Diffusion Prediction -- 4 Performance Evaluation -- 4.1 Experimental Settings -- 4.2 Overall Performance (RQ1) -- 4.3 Ablation Study (RQ2) -- 4.4 Hyperparameter Analysis (RQ3) -- 4.5 Performance in Different Scenarios (RQ4) -- 5 Related Work -- 6 Conclusion -- References -- BiasRec: A General Bias-Aware Social Recommendation Model -- 1 Introduction -- 2 Related Work -- 2.1 Bias In Recommendation System -- 2.2 Social Recommendation -- 3 Proposed Method -- 3.1 Preliminaries and General Framework -- 3.2 Data Transformation -- 3.3 Representation Learning -- 3.4 Rating Prediction -- 3.5 Loss Function -- 4 Experiment -- 4.1 Experimental Settings -- 4.2 Experimental Results -- 4.3 Ablation Experiment -- 4.4 Bias vs. Preference -- 5 Conclusion. |
References -- Beyond the Known: Novel Class Discovery for Open-World Graph Learning -- 1 Introduction -- 2 Problem Formulation -- 3 Methodology -- 3.1 Prototypical Attention Network -- 3.2 Pseudo-Label Guided Open-World Learning -- 4 Experiments -- 4.1 |
|
|
|
|
|
|
|
Experiment Settings -- 4.2 Main Results -- 4.3 Abaltion Study -- 4.4 Impact of Hyper-Parameter Settings -- 5 Related Work -- 6 Conclusion -- References -- Robust Graph Recommendation via Noise-Aware Adversarial Perturbation -- 1 Introduction -- 2 Preliminary -- 3 Proposed Methods -- 3.1 Confidence-Score Weighted Interaction Graph -- 3.2 Noise-aware Adversarial Perturbation -- 3.3 Optimization -- 4 Experiments -- 4.1 Experiment Setup -- 4.2 Overall Performance (RQ1) -- 4.3 Robustness Evaluation (RQ2) -- 4.4 Ablation Study (RQ3) -- 4.5 Further Analysis (RQ4) -- 4.6 Parameter Sensitivity (RQ5) -- 5 Related Work -- 6 Conclusion -- References -- Learning Social Graph for Inactive User Recommendation -- 1 Introduction -- 2 Industrial Observations on Social Relation -- 3 Preliminary -- 4 The Proposed Model -- 4.1 Encoding User-Item Interactions -- 4.2 Graph Structure Learning on Social Graph -- 4.3 Mimic Learning -- 4.4 Complexity Analysis -- 5 Experiments -- 5.1 Experimental Setup -- 5.2 Overall Recommendation Performance(RQ1) -- 5.3 Effects of Graph Structure Learning(RQ2) -- 5.4 Effects of Hyper-Parameters(RQ3) -- 6 Related Work -- 7 Conclusion -- References -- MANE: A Multi-cascade Adversarial Network Embedding Model for Anchor Link Prediction -- 1 Introduction -- 2 Related Work -- 3 The MANE Model -- 3.1 Model Overview -- 3.2 Problem Definition -- 3.3 Multi-cascade Network Embedding -- 3.4 Training with Adversarial Network -- 3.5 Anchor Link Prediction -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Results -- 5 Conclusion -- References. |
uTransfer: Unified Transferability Metric Incorporating Heterogeneous User Data in Social Network -- 1 Introduction -- 2 Related Work -- 2.1 Similarity Measurement -- 2.2 Transferability Measurement -- 3 Methodology -- 3.1 Problem Formulation -- 3.2 Our Method: uTransfer -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Performance Comparison -- 5 Conclusion -- References -- GPSR: Graph Prompt for Session-Based Recommendation -- 1 Introduction -- 2 Related Work -- 2.1 Session-Based Recommender Systems -- 2.2 Graph Pretraining -- 3 The Proposed GPSR Method -- 3.1 Session Graph Construction -- 3.2 Graph Model Pretraining -- 3.3 Prompt and Finetuning -- 3.4 Next-Item Prediction and Algorithm Summary -- 4 Experiments -- 4.1 Experimental Settings -- 4.2 Performance Improvement over Non-Pretraining Counterpart -- 4.3 Comparison with Baseline Methods -- 4.4 Analysis on the Basis Vector Number -- 5 Conclusion -- References -- Guiding Graph Learning with Denoised Modality for Multi-modal Recommendation -- 1 Introduction -- 2 Related Work -- 2.1 Multi-modal Recommendation -- 2.2 Graph Denoising Network -- 3 Preliminary -- 3.1 Modality-Aware User-Item Graph -- 3.2 Task Formulation -- 4 Methodology -- 4.1 Masked Modality Feature AutoEncoder -- 4.2 Modality-Guided Structure Denoising Learning -- 4.3 Cross-Modal Contrastive Aggregation -- 4.4 Prediction and Optimization -- 5 Experiments -- 5.1 Experimental Setup -- 5.2 Overall Performance -- 5.3 Ablation Study -- 5.4 Hyper-parameter Analysis -- 6 Conclusion -- References -- Enhancing Multi-view Contrastive Learning for Graph Anomaly Detection -- 1 Introduction -- 2 Related Work -- 2.1 Graph Anomaly Detection -- 2.2 Graph Contrastive Learning -- 3 Problem Formulation -- 4 Method -- 4.1 Global View Generation and Contrast Element Sample -- 4.2 Contrastive Learning Module -- 4.3 Reconstruction Module. |
4.4 Anomaly Detection Calculation -- 5 Experiments -- 5.1 Datasets -- 5.2 Experimental Settings -- 5.3 Result and Analysis -- 5.4 Ablation Study -- 5.5 Parameter Study -- 6 Conclusion -- References -- Global Route Planning for Large-Scale Requests on Traffic-Aware Road Network -- 1 Introduction -- 2 Related Work -- 2.1 Shortest Path |
|
|
|
|
|
|
|
|
|
Planning Algorithm -- 2.2 Global Route Planning Algorithm -- 3 Preliminaries -- 4 Global Path Optimization -- 4.1 Traffic Evaluation and Weight Update -- 4.2 Query Grouping -- 4.3 Initial Path Planning -- 4.4 Local Path Optimization -- 4.5 Iterative Optimization -- 5 Experimental Study -- 5.1 Experiment Settings -- 6 Conclusion -- References -- TransGAD: A Transformer-Based Autoencoder for Graph Anomaly Detection -- 1 Introduction -- 2 Related Work -- 2.1 Graph Neural Networks -- 2.2 Graph Anomaly Detection -- 2.3 Graph Transformer -- 3 Problem Formulation -- 4 Methodology -- 4.1 Neighborhood Representation Sequence -- 4.2 Transformer-Based Encoder -- 4.3 Attribute Decoder and Structure Decoder -- 4.4 Graph Anomaly Detection -- 5 Experiments -- 5.1 Dataset Description -- 5.2 Experimental Setup -- 5.3 Experimental Result -- 6 Conclusion -- References -- Unsupervised Node Clustering via Contrastive Hard Sampling -- 1 Introduction -- 2 Related Work -- 2.1 Node Clustering -- 2.2 Contrastive Learning -- 3 Problem Formulation and Preliminary -- 3.1 Graph Contrastive Learning -- 4 MeCole -- 4.1 Node-Level Fine-Grained Contrastive Learning -- 4.2 Augmentation Scheme -- 4.3 Model Overview -- 4.4 Feature Decoupling -- 4.5 Joint Learning Framework -- 4.6 Integrate Content Representations -- 4.7 Synthesizing Nodes and Contrastive Learning -- 4.8 Decoupled Cluster Module -- 4.9 Put Everything Together -- 5 Experiments -- 5.1 Experiment Results -- 5.2 Ablation Study -- 5.3 Discrepancy Functions -- 5.4 Integrate Contrastive Learning. |
5.5 Sparse Graph. |
|
|
|
|
|
|
Sommario/riassunto |
|
The seven-volume set LNCS 14850-14856 constitutes the proceedings of the 29th International Conference on Database Systems for Advanced Applications, DASFAA 2024, held in Gifu, Japan, in July 2024. The total of 147 full papers, along with 85 short papers, presented together in this seven-volume set was carefully reviewed and selected from 722 submissions. Additionally, 14 industrial papers, 18 demo papers and 6 tutorials are included. The conference presents papers on subjects such as: Part I: Spatial and temporal data; database core technology; federated learning. Part II: Machine learning; text processing. Part III: Recommendation; multi-media. Part IV: Privacy and security; knowledge base and graphs. Part V: Natural language processing; large language model; time series and stream data. Part VI: Graph and network; hardware acceleration. Part VII: Emerging application; industry papers; demo papers. |
|
|
|
|
|
|
|
| |