Distributed Multi-Task Learning with Shared Representation

2016-03-07 · Jialei Wang, Mladen Kolar, Nathan Srebro

We study the problem of distributed multi-task learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with samples for the task available locally on the machine, and study communication-efficient methods for exploiting the shared structure.

📄 PDF Abstract BibTeX arXiv:1603.02185

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Multimedia Lab @ ACL WNUT NER Shared Task: Named Entity Recognition for Twitter Microposts using Distributed Word Representations

2015-07-01 · WS 2015 7 · Fr{\'e}deric Godin, V, Baptist ersmissen, Wesley De Neve 외

named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)NER+1

Multilingual Distributed Representations without Word Alignment

2013-12-20 · Karl Moritz Hermann, Phil Blunsom

Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedn…

Cross-Lingual Document Classification Document Classification Sentence Sentiment Analysis+1

Next state prediction gives rise to entangled, yet compositional representations of objects

2024-10-07 · Tankred Saanum, Luca M. Schulze Buschoff, Peter Dayan, Eric Schulz

Compositional representations are thought to enable humans to generalize across combinatorially vast state spaces. Models with learnable object slots, which encode information about objects in separate latent codes, have…

Object

Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks

2018-04-22 · Renjie Zheng, Junkun Chen, Xipeng Qiu

Distributed representation plays an important role in deep learning based natural language processing. However, the representation of a sentence often varies in different tasks, which is usually learned from scratch and …

General Classification Multi-Task Learning Representation Learning Sentence+2

Distributed Hierarchical Temporal Memory with Shared Associative Memory for Cross-Entity Preemptive Warning

2026-06-30 · Pavia Bera, Jennifer Adorno, Sanjukta Bhanja arxiv

Anomaly detection in multivariate time series remains a critical challenge in large-scale distributed systems, where related entities may exhibit transferable precursor behavior prior to anomaly onset. Existing methods t…

Anomaly Detection