paper-with-me

Papers

Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases

2019-10-11 · Maximilian Idahl, Megha Khosla, Avishek Anand

In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide to identify subspaces in node embeddings learned from an entity graph derived from Wikipedia. We propose a method that given a concept finds a linear transformation to a subspace where the structure of the concept is retained. Our initial experiments show that we obtain low error in finding fine-grained concepts.

📄 PDF Abstract BibTeX arXiv:1910.05030

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Node Role-Guided LLMs for Dynamic Graph Clustering

2026-03-14 · Dongyuan Li, Ying Zhang, Yaozu Wu, Renhe Jiang arxiv

Dynamic graph clustering aims to detect and track time-varying clusters in dynamic graphs, revealing how complex real-world systems evolve over time. However, existing methods are predominantly black-box models. They lac…

Graph Clustering

Explainable Mapper: Charting LLM Embedding Spaces Using Perturbation-Based Explanation and Verification Agents

2025-07-24 · Xinyuan Yan, Rita Sevastjanova, Sinie van der Ben, Mennatallah El-Assady 외 arxiv

Large language models (LLMs) produce high-dimensional embeddings that capture rich semantic and syntactic relationships between words, sentences, and concepts. Investigating the topological structures of LLM embedding sp…

Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning

2025-08-03 · Xinting Huang, Michael Hahn arxiv

Understanding internal representations of neural models is a core interest of mechanistic interpretability. Due to its large dimensionality, the representation space can encode various aspects about inputs. To what exten…

Knowledge Representation with Conceptual Spaces

2018-08-01 · COLING 2018 8 · Steven Schockaert

Entity embeddings are vector space representations of a given domain of interest. They are typically learned from text corpora (possibly in combination with any available structured knowledge), based on the intuition tha…

Entity EmbeddingsInformation RetrievalInterpretable Machine LearningRepresentation Learning

DINE: Dimensional Interpretability of Node Embeddings

2023-10-02 · Simone Piaggesi, Megha Khosla, André Panisson, Avishek Anand

Graphs are ubiquitous due to their flexibility in representing social and technological systems as networks of interacting elements. Graph representation learning methods, such as node embeddings, are powerful approaches…

Graph Representation LearningLink PredictionRepresentation Learning