graph neural networks

*"GATE Data Science and Artificial Intelligence (DA) — Previous Year Papers with Solutions: A Comprehensive Guide to GATE 2024 and 2025 Question Papers, Detailed Solutions, Syllabus Overview, and Preparation Strategies for Aspirants"**

### Abbreviated Combined Title **"GATE Data Science and AI (DA) — Previous Year Papers with Solutions: A Comprehensive Guide for Aspirants"** ### Full Title with Subtitle Format **"GATE Data Science and Artificial Intelligence (DA) — Previous Year Papers with Solutions"** *Subtitle:* "A Comprehensive Guide to GATE 2024...

STSC-GNN: A sequence-derived topology-aware graph neural network for solvent-conditioned prediction of peptide structural composition

Self-Explaining Graph Neural Network for Link Prediction Based on Path-Aware Prototype Learning

Explaining black-box graph neural networks (GNNs) for link prediction (LP) remains a complicated problem. Existing explanation methods for link prediction are post-hoc and transductive, which suffer from misrepresenting the real reasoning process of the target GNN and lack of global understanding. Meanwhile, it remains...

Efficient Distributed Mini-Batch GNN Training With Decentralized Batch Processing

Distributed mini-batch Graph Neural Network (GNN) training is a crucial technique for learning large-scale graphs. Existing training methods typically rely on a centralized batch processing pipeline, where a single worker manages the entire lifespan of a batch. Consequently, the communication volume is linearly proport...

C3-Predictor: An Efficient Framework for Performance Prediction of Concurrent Queries

Query performance prediction is a challenging task in AI-enabled database (DB) research because prediction capability is crucial to optimizing DB operations (e.g., parameter optimization) and resource allocation in modern DB systems. However, existing methods often struggle to meet the flexible requirements for both pr...

Modeling Edge-Rich Graphs Using Neural Networks

The state of the art in graph analytics has advanced rapidly in recent years. Much of this advancement, to account for heterogeneous and dynamic networks, has been on graphs with rich node-level information such as those found on the Internet, social media, or in relational databases. Conversely, edge-rich graphs, wher...

Entity-Dependent Relation Learning for Knowledge Graph Completion

Knowledge graph completion (KGC) aims to predict missing relationships between pairs of entities. Recently, Message Passing Neural Networks (MPNNs) have been employed in KGC and demonstrated superior ability in embedding learning. Current methods, however, face two major dilemmas. One focuses on learning complex entity...

AI-Driven Genomic and Proteomic Insights in Dermatological Disorders

Dermatological disorders represent a massive global health burden, affecting approximately 2 billion people, yet conventional diagnosis often relies on morphology, leading to unpredictable, “trial-and-error” treatment. This necessitates a shift toward precision dermatology, leveraging the genomic and proteomic data tha...

Graph neural network-based surrogate models for thin-walled structural analysis with application to ship hull structures

Iterative structural design and optimization of ship hulls at the early design stage require many structural analysis evaluations. Finite element analysis (FEA) is the standard tool for evaluating stress and displacement fields, but it is computationally prohibitive at the scale required by design optimization. Existin...

Particle tracking in quantitative microscopy: a modular tutorial on classical and deep learning methods

Particle tracking is a central tool in digital microscopy for quantifying micro- and nanoscale dynamics. Selecting and validating appropriate methods remains challenging, particularly under low signal-to-noise ratios or high particle densities and for researchers with limited computational expertise. In this talk, we p...

STD-Net support-aware dual-graph learning

Support-aware dual-graph neural network software for spatial transcriptomic cell-type deconvolution. This release contains the support_rare_balanced implementation, paper-aligned wrappers and tests; input data and numerical results are intentionally excluded.

Drug Repositioning Through Interpretable Link Prediction in Drug–Disease Networks