← Back to all news
arXiv Computer Vision

Tensor Decomposition Structure Search Framework from an Interaction Perspective

Related stories

arXiv AI
Oct 9

HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling

The paper introduces HRIL, a method for learning multimodal representations that explicitly models higher‑order interactions among modalities using a cross‑moment tensor and Tucker decomposition. It adds a synergy‑aware regularizer to preserve higher‑order coupling capacity, aiming to capture synergistic signals that only emerge from joint configurations of multiple modalities. Experiments on controlled synergy tasks and real‑world benchmarks show consistent improvements over existing multimodal contrastive methods, especially on tasks dominated by synergistic interactions.

By Qun Dai, Liangjian Wen, Jiang Duan, Yong Dai, Dongkai Wang, Maolin Wang, Mingjie Wang, Jianzhuang Liu, He Yan, Zhao Kang
ragmultimodalbenchmarks
More like this →
Hugging Face Trending Papers
Sep 2

Coupled Tensor-Tensor Completion Method with Applications in Drug Repurposing

The paper introduces Coupled Tensor‑Tensor Completion (CTTC), a new framework that incorporates side information in tensor form to enhance tensor completion tasks. CTTC leverages hidden connections among multimodal tensors and is grounded in distance metric learning and group theory. Experiments on the DTD and LINCS datasets show that CTTC outperforms existing methods such as HaLRTC, CTRC, Cell, and NTDDR in both run‑time and root‑sum‑of‑errors accuracy for predicting drug effects.

multimodalbenchmarks
More like this →
arXiv Machine Learning
Sep 4

Coupled Tensor-Tensor Completion Method with Applications in Drug Repurposing

The paper introduces Coupled Tensor‑Tensor Completion (CTTC), a new framework that incorporates side information in tensor form to enhance tensor completion tasks. CTTC leverages hidden connections among multimodal tensors and is grounded in distance metric learning and group theory. Experiments on the DTD and LINCS datasets show that CTTC outperforms existing methods such as HaLRTC, CTRC, Cell, and NTDDR in both runtime and root‑sum‑of‑squares error for drug effect prediction.

By Maryam Bagherian, Albert Hung, Ivo Dinov, Joshua Welch
multimodalbenchmarks
More like this →
arXiv AI
Sep 1

Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability

This survey reviews tensor methods applied to large language models, framing them through a seven‑stage lifecycle (tokenization, embeddings, pre‑training, adaptation, compression, inference, interpretability) and a component view (embeddings, attention, feed‑forward networks). It offers unified notation, theoretical foundations, and comparative analyses of tensorization strategies for Transformer components, while highlighting evaluation protocol differences and model scale effects. The paper also introduces a new metric, ρ_gap, to quantify the gap between theoretical memory savings and actual system‑level speedup, and connects tensor techniques to related efficiency and probabilistic methods.

By Matvei Tarasov, Salman Ahmadi-Asl, Andre L. F. de Almeida, Andrzej Cichocki
llmsragnlpsafety
More like this →
arXiv Statistics ML
Sep 22

Tensor Completion using Subspace Information

Tensor Completion using Subspace Information (TCSI) is an algorithm that leverages side information by estimating a subspace and reformulating tensor completion as a matrix regression problem. Theoretical analysis shows that accurate subspace information reduces sample complexity to nearly linear in the uncoupled ambient dimensions and relaxes signal-to-noise ratio requirements compared to existing guarantees. Numerical simulations and an application to reconstructing global Total Electron Content (TEC) maps demonstrate lower reconstruction errors than competing methods.

By Jingyang Li, Michael K. Ng
More like this →