Research map / Graph learning / Knowledge and temporal graphs
ContextGraph: Lifelog Intelligence Framework for Contextual Subgraph Evolution
Anil Sharma, Gunturi Venkata Sai Phani Kiran, Jayesh Rajkumar Vachhani, Sourabh Vasant Gothe, Ayon Chattopadhyay, Yashwant Saini, Parameswaranath Vadackupurath Mani, Barath Raj Kandur Raja
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Temporal-VAE embedding to Context-GVAE (ablation) | DCE · OOD TPP-derived | F1: 0.446 -> 0.708 | Improved |
| add Context-GVAE embedding to Temporal-VAE (ablation) | DCE · OOD TPP-derived | F1: 0.733 -> 0.708 | Hurt |
| add Context-GVAE embedding to Temporal-VAE (ablation) | DCE · 6 simulated activity classes | inter-class distance: 1.130 -> 1.144 | Improved |
| add Context-GVAE embedding to Temporal-VAE (ablation) | DCE · 6 simulated activity classes | intra-class distance: 0.031 -> 0.056 | Hurt |
| use DCE embeddings instead of Node2Vec (ablation) | Node2Vec · OOD TPP-derived | F1: 0.562 -> 0.708 | Improved |
| use DCE embeddings instead of HAN | HAN · OOD TPP-derived | F1: 0.341 -> 0.708 | Improved |
| use DCE embeddings instead of Node2Vec/DeepWalk | Node2Vec/DeepWalk · single graph | embedding time (s): 100 -> 8 | Improved |
| use frequency-based change-point features (PELT) instead of DCE | PELT · OOD TPP-derived | F1: 0.708 -> 0.461 | Hurt |
Closest papers by meaning
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.83)
- EgoLife: Towards Egocentric Life Assistant (CVPR 2025 · similarity 0.82)
- DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs (NeurIPS 2025 · similarity 0.82)
- Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs (NeurIPS 2026 · similarity 0.82)
- PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling (NeurIPS 2025 · similarity 0.81)
- Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models (NeurIPS 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
