arXiv research

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

The paper studies how points and lines can move while preserving incidences.

We develop a transitional geometry, that is, a family of geometries of constant curvatures which makes a continuous connec-tion between the hyperbolic, Euclidean and spherical geometries. In this transitional setting, several geometric entities like points, lines, dis-tances, triangles, angles, area, curvature, etc. as…

Minimal generating sets found for Kim-Manturov groups.

New tiling algorithm for hyperbolic 3-manifolds, characterizing cusp areas.

Instanton bundles on $\mathbb{P}^3$ have been at the core of the research in Algebraic Geometry during the last thirty years. Motivated by the recent extension of their definition to other Fano threefolds of Picard number one, we develop the theory of instanton bundles on the complete flag variety $F:=F(0,1,2)$ of poin…

New algorithms reduce communication costs in collaborative learning.

Supply Chain Management often requires independent organizations to work together to achieve shared objectives. This collaboration is necessary when coordinated actions benefit the group more than the uncoordinated efforts of individual firms. Despite the commonly reported benefits that can be gained in close relations…

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…

The geometry of cosets in the subgroups H of the two-generator free group G =\textless{} a, b \textgreater{} nicely fits, via Grothendieck's dessins d'enfants, the geometry of commutation for quantum observables. Dessins stabilize point-line incidence geometries that reflect the commutation of (generalized) Pauli opera…

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…

Paper tackles unobserved confounding in human-AI collaborations.

Firms' collaboration networks can decline but remain resilient.

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

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

Advances in collaborative filtering and ranking methods.

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

The paper explains the topological origin of the distinction between incidence theorems over division rings and fields.

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…

Collaborative recommendation is an information-filtering technique that attempts to present information items (movies, music, books, news, images, Web pages, etc.) that are likely of interest to the Internet user. Traditionally, collaborative systems deal with situations with two types of variables, users and items. In…

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 way developers collaborate inside and particularly across teams often escapes management's attention, despite a formal organization with designated teams being defined. Observability of the actual, organically formed engineering structure provides decision makers invaluable additional tools to manage their talent p…

Meta clustering categorizes learners for collaborative learning.

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

Partner-aware algorithms improve AI collaboration in multi-agent settings.

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

Today, the prominence of data science within organizations has given rise to teams of data science workers collaborating on extracting insights from data, as opposed to individual data scientists working alone. However, we still lack a deep understanding of how data science workers collaborate in practice. In this work…

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

New algorithms for collaborative learning in uncertain, decentralized environments.

New algorithms balance collaboration and adversarial behavior in linear bandits.

Game theory models incentivizes honesty in collaborative learning among competitors.

Collaborative filtering is used to recommend items to a user without requiring a knowledge of the item itself and tends to outperform other techniques. However, collaborative filtering suffers from the cold-start problem, which occurs when an item has not yet been rated or a user has not rated any items. Incorporating …

Enhances student diversity in collaborative learning.

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…

Enhances financial analysis with multi-agent collaboration.

Collaborative filtering is a rapidly advancing research area. Every year several new techniques are proposed and yet it is not clear which of the techniques work best and under what conditions. In this paper we conduct a study comparing several collaborative filtering techniques -- both classic and recent state-of-the-…

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

This work advances collaborative decision making by combining human and AI strengths in uncertainty quantification.

Latent factor models have been used widely in collaborative filtering based recommender systems. In recent years, deep learning has been successful in solving a wide variety of machine learning problems. Motivated by the success of deep learning, we propose a deeper version of latent factor model. Experiments on benchm…

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…

This paper advances theory on the process of collaboration between entities and its implications on the quality of services, information, and/or products (SIPs) that the collaborating entities provide to each other. It investigates the scenario of outsourced IS projects (such as custom software development) where the e…

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

Develops NFCF to reduce gender bias in social media recommendation systems.

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…

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

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…

The "dancing metric" is a pseudo-riemannian metric $\pmb{g}$ of signature $(2,2)$ on the space $M^4$ of non-incident point-line pairs in the real projective plane $\mathbb{RP}^2$. The null-curves of $(M^4,\pmb{g})$ are given by the "dancing condition": the point is moving towards a point on the line, about which the li…

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