26 papers
DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
Xin Li, Jin Li, Shoujin Wang +2
Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically lev…
The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning
Xin Li
Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow linearly with time, eventually forci…
Associative Memory for Non-Stationary Environments: A Self-Sizing Generalization of Hopfield Networks
Xin Li
The Hopfield network made associative memory (AM) the model system of neural computation, but it solves the problem only for a \emph{stationary} world: a fixed set of memories, sto…
The Urysohn Machine: A Metric-Topological Model of Computation
Xin Li
We introduce the Urysohn Machine, an effective model of classification-oriented computation in which metric separation, frontier structure, and contraction are explicit parts of th…
Persistent Homology as a Theory of Emergent Structure
Xin Li
Why do some macroscopic structures remain identifiable even though their microscopic constituents continually change? Vortices persist while fluid parcels turn over, neural memorie…
Structural Decoupling: A Scaffold-Flow Theory of Generalization and Alignment
Xin Li
Learning in non-stationary and multi-context environments requires more than ordinary within-task generalization. A system must also discover which contexts exist, route inputs to…