arXiv research

New model for multiplex networks learns shared structure.

HCL learns shared and modality-specific latent representations for multimodal data.

Surveying joint Gaussian graphical models to identify shared structures across domains.

New algorithm reduces multi-agent bandit regret by sharing data.

Model improves covariance estimation from shared and distinct datasets.

New method learns shared structures in non-linear tasks.

The paper optimizes risk-sharing in decentralized networks.

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 sa…

The paper finds infinite pairs of CP1-structures sharing same holonomy.

New model extracts shared brain activity patterns from fMRI data.

We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes eve…

The increased availability of the multi-view data (data on the same samples from multiple sources) has led to strong interest in models based on low-rank matrix factorizations. These models represent each data view via shared and individual components, and have been successfully applied for exploratory dimension reduct…

We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks. We exploit the intuition that for domain adaptation, we wish to share classifier structure, but for multitask learning, we wish to share covariance structure. Our hierarchical model is seen to subsume several previous…

Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity of parallel ordering for deep MTL is first tested by comparing it with permuted ordering of shared la…

The large majority of risk-sharing transactions involve few agents, each of whom can heavily influence the structure and the prices of securities. This paper proposes a game where agents' strategic sets consist of all possible sharing securities and pricing kernels that are consistent with Arrow-Debreu sharing rules. F…

MT-HAL learns features and task associations for multiple tasks with a shared sparse structure.

The creation of social ties is largely determined by the entangled effects of people's similarities in terms of individual characters and friends. However, feature and structural characters of people usually appear to be correlated, making it difficult to determine which has greater responsibility in the formation of t…

The paper addresses risk sharing and variability measures among agents with general risk preferences.

Researchers develop a method to measure treatment effects in settings with shared states.

This paper analyzes the quantitative relations between stock prices and quantities of tradable stock shares in Chinese stock markets at six time points by means of Exploratory Data Analysis (EDA) method. It is found the resulting formulae have the same structure but different parameters. This paper also uses these rela…

A framework for multilayer networks predicts links without shared structures.

CMF is a technique for simultaneously learning low-rank representations based on a collection of matrices with shared entities. A typical example is the joint modeling of user-item, item-property, and user-feature matrices in a recommender system. The key idea in CMF is that the embeddings are shared across the matrice…

UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.

In increasingly many settings, data sets consist of multiple samples from a population of networks, with vertices aligned across these networks. For example, brain connectivity networks in neuroscience consist of measures of interaction between brain regions that have been aligned to a common template. We consider the …

This paper analyzes P2P collaborative insurance products and network structure impact.

New method identifies shared components from unpaired multimodal mixtures.

Paper tackles robust decision-making from multiple sites with shared structure.

Paper provides new bounds for risk aggregation and sharing.

First-order ANIL learns shared representations even with overparametrization.

CoreFlow models matrix-valued distributions efficiently, preserving shared low-rank structure.

Consensus dimension reduction combines multiple visualizations to identify shared patterns.

Analyzing multivariate time series data is important to predict future events and changes of complex systems in finance, manufacturing, and administrative decisions. The expressiveness power of Gaussian Process (GP) regression methods has been significantly improved by compositional covariance structures. In this paper…

GDA-HIN adapts across heterogeneous networks by aligning shared and private node types.

Diffusion models adapt to low-dimensional structures for nonparametric density estimation.

Kernel method embeds noisy datasets, capturing shared structures.

L2O uses ML to optimize traditional optimization techniques.

IPGP framework improves psychological assessment by integrating shared and unique traits.

The paper improves classification accuracy by leveraging a shared signal across domains in high-dimensional classification.

This paper considers the multi-task learning problem and in the setting where some relevant features could be shared across few related tasks. Most of the existing methods assume the extent to which the given tasks are related or share a common feature space to be known apriori. In real-world applications however, it i…

The paper explores methods to better estimate treatment effects by leveraging shared structure in potential outcomes.

A new model detects common patterns in pollination networks.

Enhances generative model accuracy through knowledge transfer.

DeepSeekMoE improves language model efficiency with shared experts and normalized gating.

Training-free source selection for LLM families with shared vocabularies

Shared workspace improves neural module coordination in deep learning.

Proposes EOT eigenmaps for aligning and embedding multiple datasets.

A new method for analyzing multi-source, multi-way data reduces dimensionality and reveals shared and individual structures.

Unified MTL framework for heterogeneous data integrates shared and task-specific encoders.