arXiv research

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

Market incentivizes parties to share high-quality data for collaborative machine learning tasks.

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…

CoLoRA leverages task similarity to boost fine-tuning efficiency.

Enhances student diversity in collaborative learning.

Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.

Enhances financial analysis with multi-agent collaboration.

Framework allows organizations to collaborate on learning tasks securely.

Game theory models incentivizes honesty in collaborative learning among competitors.

A novel method for efficient CDRL over wireless networks.

This study proposes a deep learning framework using ResNeXt for efficient financial data mining.

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

We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative effects into …

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

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…

Novel method reduces radiomic data annotation needs.

Advances in collaborative filtering and ranking methods.

RGCF improves collaborative filtering by refining graph convolution embeddings.

A framework for collaborative learning reduces communication rounds.

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…

Distributed adaptive networks achieve better estimation performance by exploiting temporal and as well spatial diversity while consuming few resources. Recent works have studied the single task distributed estimation problem, in which the nodes estimate a single optimum parameter vector collaboratively. However, there …

Hyperbolic geometry autoencoder outperforms Euclidean in top-N recommendation tasks.

DiCE uses diverse agents to explore and learn, avoiding local minima.

Drone optimizes collaborative learning for neural networks.

In today's day and age when almost every industry has an online presence with users interacting in online marketplaces, personalized recommendations have become quite important. Traditionally, the problem of collaborative filtering has been tackled using Matrix Factorization which is linear in nature. We extend the wor…

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…

Co-PLNet combines point and line predictions to improve wireframe parsing accuracy and efficiency.

Split learning improves deep learning in healthcare by sharing data.

New collaborative algorithm improves personalized mean estimation in online settings.

A new KD model for collaborative filtering improves top-N recommendation performance.

OpenML is an online machine learning platform where researchers can easily share data, machine learning tasks and experiments as well as organize them online to work and collaborate more efficiently. In this paper, we present an R package to interface with the OpenML platform and illustrate its usage in combination wit…

Collaborative filtering (CF) is a popular technique in today's recommender systems, and matrix approximation-based CF methods have achieved great success in both rating prediction and top-N recommendation tasks. However, real-world user-item rating matrices are typically sparse, incomplete and noisy, which introduce ch…

In many applications requiring multiple inputs to obtain a desired output, if any of the input data is missing, it often introduces large amounts of bias. Although many techniques have been developed for imputing missing data, the image imputation is still difficult due to complicated nature of natural images. To addre…

A deep RL approach learns multi-agent coordination through dynamic graph communication.

A new model combines Gaussian processes with collaborative filtering for uncertainty-aware recommendations.

NKI integrates obfuscated datasets using nonlinear kernels for improved data collaboration.

Graph-based LRE estimates likelihood-ratios collaboratively for nodes.

OL4EL optimizes edge learning on resource-constrained servers.

New federated $f$-differential privacy for collaborative learning.

Paper proposes methods to reduce bias and variance in recommender systems.

In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) …

Paper tackles medical image diagnosis with unsupervised domain adaptation.

Tensor factorization has been demonstrated as an efficient approach for computational phenotyping, where massive electronic health records (EHRs) are converted to concise and meaningful clinical concepts. While distributing the tensor factorization tasks to local sites can avoid direct data sharing, it still requires t…

A new machine learning framework called machine collaboration improves prediction accuracy.

New algorithms reduce communication costs in collaborative learning.

This paper proposes CF-NADE, a neural autoregressive architecture for collaborative filtering (CF) tasks, which is inspired by the Restricted Boltzmann Machine (RBM) based CF model and the Neural Autoregressive Distribution Estimator (NADE). We first describe the basic CF-NADE model for CF tasks. Then we propose to imp…

Framework uses human judgment to distinguish algorithmically indistinguishable cases.

Hybrid methods that utilize both content and rating information are commonly used in many recommender systems. However, most of them use either handcrafted features or the bag-of-words representation as a surrogate for the content information but they are neither effective nor natural enough. To address this problem, w…