← Back to all news
arXiv Machine Learning By Archish S, Sabyasachi Basu, Ankit Garg, Ravishankar Krishnaswamy, Kirankumar Shiragur

EigenLI: Spectral Approximations to Late Interaction

Read the original on arXiv Machine Learning →

EigenLI introduces a spectral approximation framework that compresses late‑interaction representations by identifying document‑specific low‑dimensional subspaces. By selecting dominant eigendirections, it constructs reduced interaction representations that outperform clustering‑based pooling methods on ColBERTv2 and AnswerAI‑ColBERT‑small. The framework also yields EigenLI‑SV, a single‑vector ANN‑compatible representation that consistently surpasses comparable surrogates such as MUVERA across multiple datasets and text models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
5d ago

A Manifold-Aware Topic Modeling Approach via Rank-Based Prototypes

The paper introduces MARETopic, a training‑free framework that identifies topics by selecting rank‑based prototype documents from pretrained embeddings. By projecting embeddings onto a low‑dimensional manifold and building ranked neighborhood lists, a greedy algorithm picks exactly K exemplar texts whose neighborhoods cover the corpus. Two variants—MARETopic_Corr, which uses a query‑performance predictor and rank correlation, and MARETopic_Diff, which employs a rank‑based diffusion matrix—achieve higher purity and NMI on benchmark datasets and run significantly faster, while also improving topic coherence and vocabulary diversity through a novel Maximal Marginal Relevance step.

By Thiago C\'esar Castilho Almeida, Daniel Carlos Guimar\~aes Pedronette
ragdiffusionbenchmarks
More like this →
arXiv AI
Sep 18

Randomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices

The paper introduces two randomized approaches to accelerate spectral co‑clustering of word‑document matrices: one based on randomized SVD via random projection, and another combining partial SVD with element‑wise random sampling. Experiments on real and synthetic data show both methods cut runtime compared to full SVD, with the projection technique offering more consistent performance across varied sparsity levels, while the sampling method excels on denser matrices. The study highlights that the choice of approximation should align with the data’s structural properties.

By Fateme Mazdarani, Carlos Toxtli
efficiency
More like this →