analiza aiqbench
EvtGraph introduces a novel framework that optimizes multimodal temporal learning by compressing dense sequences into salient event tokens under strict computational budgets. By shifting from uniform discretization to sparse graph reasoning over critical transitions, the method achieves superior efficiency and accuracy on clinical benchmarks like MIMIC-IV compared to standard Transformer architectures. This approach offers a practical paradigm for managing high-redundancy data where representational capacity is limited.
EvtGraph: Event-Adaptive Compression for Sparse Temporal Graph Learning in Multimodal Time Series
arXiv:2608.04368v1 Announce Type: new Abstract: Multimodal temporal data are inherently irregular and uneven in information density, yet most models rely on uniform discretization, leading to inefficient representations. We propose \textbf{EvtGraph}, a unified framework that aligns computation with temporal salience under explicit budget constraints. EvtGraph reparameterizes sequences into event-level tokens via event-adaptive compression (EAMC), selects a compact subset with a node budget (NBC), and performs temporally constrained sparse graph reasoning (T2SG). This transforms dense sequences into structured computation over salient events, reducing complexity while preserving critical transitions. We show that this design provides a practical mechanism for allocating representational capacity under a fixed budget, yielding a consistent performance--efficiency trade-off, where a small budget is often sufficient in practice. Experiments on multimodal clinical (MIMIC-IV + CXR) and cross-domain benchmarks demonstrate that EvtGraph outperforms both Transformer-based and recurrent baselines while significantly improving efficiency. These results suggest that budget-constrained event-centric representation provides a general paradigm for learning from high-redundancy temporal data.
Abstract:Multimodal temporal data are inherently irregular and uneven in information density, yet most models rely on uniform discretization, leading to inefficient representations. We propose \textbf{EvtGraph}, a unified framework that aligns computation with temporal salience under explicit budget constraints. EvtGraph reparameterizes sequences into event-level tokens via event-adaptive compression (EAMC), selects a compact subset with a node budget (NBC), and performs temporally constrained sparse graph reasoning (T2SG). This transforms dense sequences into structured computation over salient events, reducing complexity while preserving critical transitions. We show that this design provides a practical mechanism for allocating representational capacity under a fixed budget, yielding a consistent performance--efficiency trade-off, where a small budget is often sufficient in practice. Experiments on multimodal clinical (MIMIC-IV + CXR) and cross-domain benchmarks demonstrate that EvtGraph outperforms both Transformer-based and recurrent baselines while significantly improving efficiency. These results suggest that budget-constrained event-centric representation provides a general paradigm for learning from high-redundancy temporal data.
Machine Learning (cs.LG)
arXiv:2608.04368 [cs.LG]
(or arXiv:2608.04368v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.04368 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 246 cuvinte
Subiecte conexe
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · 15 iul. 2026
BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting
arXiv · 26 sept. 2026
LLMODE: Aligning ODEs with LLMs via Gated Token Injection for Irregular Spatio-Temporal Forecasting
arXiv · 1 sept. 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · 12 iun. 2026