5 papers
Topological measures in weighted hypergraphs
Ekaterina Vasilyeva, Liubov Tupikina, Daniil Musatov +3
Higher-order interactions introduce an additional structural dimension to complex networks, requiring consistent generalizations of classical topological measures. In hypergraphs,…
Thinking Before Constraining: A Unified Decoding Framework for Large Language Models
Ngoc Trinh Hung Nguyen, Alonso Silva, Laith Zumot +3
Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes outputs difficult to verify. Conversely,…
Iterative Ricci-Foster Curvature Flow with GMM-Based Edge Pruning: A Novel Approach to Community Detection
Arsenii Onuchin, Konstantin Sorokin, Maxim Beketov +1
Community detection in complex networks is a fundamental problem, open to new approaches in various scientific settings. We introduce a novel community detection method, based on R…
Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods
Xiaohua Lu, Liubov Tupikina, Mehwish Alam
Real-world knowledge can take various forms, including structured, semi-structured, and unstructured data. Among these, knowledge graphs are a form of structured human knowledge th…
Dissecting embedding method: learning higher-order structures from data
Liubov Tupikina, Kathuria Hritika
Active area of research in AI is the theory of manifold learning and finding lower-dimensional manifold representation on how we can learn geometry from data for providing better q…