arXiv research

New algorithms reduce communication costs in collaborative learning.

PCL tackles collaborative learning for diverse agents, reducing sample complexity.

Study collaborative learning among multi-agents in multi-armed bandits.

A new privacy-preserving deep learning scheme for asymmetrically collaborative machine learning.

Game theory models incentivizes honesty in collaborative learning among competitors.

Proposes a deep latent factor model for better recommendation systems.

New algorithms for collaborative learning in uncertain, decentralized environments.

This paper considers the problem of high dimensional signal detection in a large distributed network whose nodes can collaborate with their one-hop neighboring nodes (spatial collaboration). We assume that only a small subset of nodes communicate with the Fusion Center (FC). We design optimal collaboration strategies w…

Meta clustering categorizes learners for collaborative learning.

DEMVC improves multi-view clustering with collaborative training and deep autoencoders.

Collaborative filtering (CF) has been successfully employed by many modern recommender systems. Conventional CF-based methods use the user-item interaction data as the sole information source to recommend items to users. However, CF-based methods are known for suffering from cold start problems and data sparsity proble…

The excellent performance of representation learning of autoencoders have attracted considerable interest in various applications. However, the structure and multi-local collaborative relationships of unlabeled data are ignored in their encoding procedure that limits the capability of feature extraction. This paper pre…

Enhances student diversity in collaborative learning.

We study the collaborative PAC learning problem recently proposed in Blum et al.~\cite{BHPQ17}, in which we have $k$ players and they want to learn a target function collaboratively, such that the learned function approximates the target function well on all players' distributions simultaneously. The quality of the col…

Can health entities collaboratively train deep learning models without sharing sensitive raw data? This paper proposes several configurations of a distributed deep learning method called SplitNN to facilitate such collaborations. SplitNN does not share raw data or model details with collaborating institutions. The prop…

Optimal algorithm found for collaborative learning in bandits with optimal regret bounds.

A new method for online personalized learning reduces gradient variance by dynamically selecting peers.

In this paper we examine the effect of applying ensemble learning to the performance of collaborative filtering methods. We present several systematic approaches for generating an ensemble of collaborative filtering models based on a single collaborative filtering algorithm (single-model or homogeneous ensemble). We pr…

Algorithm optimizes collaborative learning among distributed clients using kernel-based bandits.

FL improves insurance claims loss prediction without sharing data.

A novel federated learning framework resolves structural misalignment in model fusion.

Paper tackles unobserved confounding in human-AI collaborations.

A framework for collaborative learning reduces communication rounds.

Split learning improves deep learning in healthcare by sharing data.

Machine learning assesses group collaboration in classrooms.

New method for collaborative learning with multiple distributions, minimizing sample size.

OL4EL optimizes edge learning on resource-constrained servers.

Backdoor attacks are possible in feature-partitioned collaborative learning, even without labels.

Collaborative filtering (CF) and content-based filtering (CBF) have widely been used in information filtering applications. Both approaches have their strengths and weaknesses which is why researchers have developed hybrid systems. This paper proposes a novel approach to unify CF and CBF in a probabilistic framework, n…

Collaborative filtering (CF) is a successful approach commonly used by many recommender systems. Conventional CF-based methods use the ratings given to items by users as the sole source of information for learning to make recommendation. However, the ratings are often very sparse in many applications, causing CF-based …

AdaDKRR tackles data silos by combining autonomy, privacy, and collaboration.

Framework allows organizations to collaborate on learning tasks securely.

We study a recent model of collaborative PAC learning where $k$ players with $k$ different tasks collaborate to learn a single classifier that works for all tasks. Previous work showed that when there is a classifier that has very small error on all tasks, there is a collaborative algorithm that finds a single classifi…

Proposes TFCL to mitigate negative transfer in MTL by collaborating across features and tasks.

Novel method reduces radiomic data annotation needs.

In this work, we define a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers. We focus on consensus super teaching. It aims at organizing distributed teachers to jointly select a compact while informative training subset from data hosted by the teachers to make a learner l…

We introduce collaborative learning in which multiple classifier heads of the same network are simultaneously trained on the same training data to improve generalization and robustness to label noise with no extra inference cost. It acquires the strengths from auxiliary training, multi-task learning and knowledge disti…

CFFL framework improves fairness in FL without sacrificing accuracy.

This work proposes a collaborative multi-head attention layer to reduce model size without sacrificing accuracy.

A novel method for efficient CDRL over wireless networks.

Paper proposes efficient privacy-preserving matrix encryption for secure collaborative learning against malicious adversaries.

We address challenges in collaborative black-box optimization through three frameworks.

We learn hierarchical slate representations for collaborative filtering.

JPS improves joint policies for multi-agent collaboration in imperfect information games.

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models that leverage a collaboration graph describing the relationships between user per…

This study optimizes model averaging for personalized collaborative learning.

Asynchronous algorithms reduce privacy costs in distributed machine learning.

Paper proposes FedAMP for improved federated learning with non-IID data.