UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure
Quick Answer
UniSAGE introduces a unified framework for modeling hierarchical data with static and dynamic attributes, outperforming existing methods by over 10% on multiple benchmarks.
Quick Take
UniSAGE introduces a unified framework for modeling hierarchical data with static and dynamic attributes, outperforming existing methods by over 10% on multiple benchmarks. It automates the representation of complex cross-attribute dependencies and adapts to evolving data schemas, making it robust for real-world applications.
Key Points
- UniSAGE constructs a global attribute graph for hierarchical and temporal relationships.
- It introduces two orthogonal parameter subspaces for static aggregation and dynamic reasoning.
- The framework enables task-specific interactions between static and dynamic attributes.
- Extensive experiments show over 10% performance improvement on various tasks.
- UniSAGE is fully automated and robust to evolving data schemas.
Paper Resources
📖 Reader Mode
~2 min readAbstract:With the rapid growth of digital data, real-world applications increasingly involve hierarchical information that combines static attributes with dynamic records. Modeling such heterogeneous data in a unified and generalizable manner remains challenging. Existing approaches often rely on extensive manual design, are tightly coupled to specific data schemas, and typically process static and dynamic attributes in isolation, thereby overlooking their implicit interactions. We propose UniSAGE, a unified framework for modeling data with both static and dynamic attributes. UniSAGE constructs a global attribute graph that represents hierarchical and temporal relationships in a unified structure. To ensure representational consistency, it introduces two orthogonal parameter subspaces that jointly support static aggregation and dynamic reasoning within a shared semantic space. Building on these unified representations, UniSAGE further enables task-specific interaction between static and dynamic attributes via a lightweight hyper-structure mechanism. UniSAGE is fully automated, robust to evolving data schemas, and capable of capturing complex cross-attribute dependencies. Extensive experiments on multiple public benchmarks and a real-world financial behavior dataset demonstrate that UniSAGE consistently outperforms existing methods, achieving performance improvements of over 10% on several tasks.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.14102 [cs.CL] |
| (or arXiv:2607.14102v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.14102 arXiv-issued DOI via DataCite |
Submission history
From: Taoran Fang [view email]
[v1]
Wed, 6 May 2026 07:48:48 UTC (209 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
The study evaluates three NLP approaches—Named Entity Recognition, Keyword Extraction, and Topic Modelling—using the Their Finest Hour Online Archive to automate keyword extraction from crowdsourced WWII collections. Findings suggest that while NLP methods show promise, no single approach is sufficient, and ethical considerations in automated keyword extraction are crucial for responsible stewardship.