Latest Research in Machine Learning

Top Research Topics in Machine Learning

• Machine Learning — 17 papers
• Artificial Intelligence — 4 papers
• Advanced Graph Neural Networks — 3 papers
• Explainable Artificial Intelligence (XAI) — 1 papers
• Computation and Language — 1 papers
• Game Theory and Voting Systems — 1 papers
• Social and Information Networks — 1 papers
• Databases — 1 papers
• Performance — 1 papers

Highest-Cited Papers

1. On the Minimization of Graph Counterfactual Explanations: Theory and a Local Bounded Search Algorithm
2. Incremental Graph Construction Enables Robust Spectral Clustering of Texts
3. Fair Graph Learning Needs Expressiveness: Rethinking Fairness from the Spectral Perspective
4. ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation
5. Symmetries and Singularities
6. Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks
7. Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation
8. GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs
9. Training-free ranking from pairwise comparisons via acyclic graph construction
10. Multi-Agent Agentic Graph Learning via Structural Signatures
11. Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning
12. $α$-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph Modeling
13. LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models
14. A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit
15. MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks
16. When Vision Meets Graphs: A Survey on Graph Reasoning and Learning
17. Dual-Metric Partitioning with Adaptive Kernel Execution for Efficient GCN Acceleration
18. One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models
19. FloydNet: A Learning Paradigm for Global Relational Reasoning
20. Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training