#temporal-graphs News & Analysis

4 articles tagged with #temporal-graphs. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · Jun 27/10

🧠

Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents

Researchers propose InKH, an architecture for financial AI agents that maintains persistent context about users, portfolios, and market conditions rather than forcing users to repeatedly restate information. In controlled benchmarks, InKH achieves 82% latency reduction and 96% improvement in stale-knowledge elimination compared to existing approaches, suggesting that AI financial tools succeed by absorbing operational complexity into their systems rather than delegating it to users.

AINeutralarXiv – CS AI · Jun 236/10

🧠

Temporal Graph Pattern Machine

Researchers introduce Temporal Graph Pattern Machine (TGPM), a foundation framework that learns generalized evolving patterns in dynamic networks using Transformer architecture and self-supervised pre-training. The model achieves top performance on temporal link prediction and node classification tasks while demonstrating strong cross-domain transferability, addressing limitations of existing task-centric approaches.

AINeutralarXiv – CS AI · Jun 236/10

🧠

A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction

Researchers present a hybrid TGN-SEAL model that improves link prediction in dynamic, sparse networks by combining Temporal Graph Networks with enclosing subgraph extraction. The approach achieves at least 2% average precision improvement over standard TGNs on sparse datasets like CDRs and email networks, addressing a key limitation in temporal graph analysis.

AINeutralarXiv – CS AI · Jun 105/10

🧠

Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport

Researchers introduce Temporal Sheaf Neural Networks (TSNN), a novel framework for temporal link prediction that uses time-varying orthogonal coordinate frames to compare node states rather than operating in a shared global embedding space. The model demonstrates competitive performance on multiple benchmarks while offering theoretical guarantees on convergence and stability, with particular strength on heterogeneous graphs.