Data generation for machine learning interatomic potentials and beyond

M Kulichenko, B Nebgen, N Lubbers, JS Smith… - Chemical …, 2024 - ACS Publications
The field of data-driven chemistry is undergoing an evolution, driven by innovations in
machine learning models for predicting molecular properties and behavior. Recent strides in …

Active learning strategies for atomic cluster expansion models

Y Lysogorskiy, A Bochkarev, M Mrovec, R Drautz - Physical Review Materials, 2023 - APS
The atomic cluster expansion (ACE) was proposed recently as a new class of data-driven
interatomic potentials with a formally complete basis set. Since the development of any …

Preference elicitation as an optimization problem

A Sepliarskaia, J Kiseleva, F Radlinski… - Proceedings of the 12th …, 2018 - dl.acm.org
The new user coldstart problem arises when a recommender system does not yet have any
information about a user. A common solution to it is to generate a profile by asking the user …

Reduced-order modeling of deep neural networks

J Gusak, T Daulbaev, E Ponomarev, A Cichocki… - Computational …, 2021 - Springer
We introduce a new method for speeding up the inference of deep neural networks. It is
somewhat inspired by the reduced-order modeling techniques for dynamical systems. The …

Cold-start Recommendation by Personalized Embedding Region Elicitation

HT Nguyen, D Nguyen, K Doan, VA Nguyen - arXiv preprint arXiv …, 2024 - arxiv.org
Rating elicitation is a success element for recommender systems to perform well at cold-
starting, in which the systems need to recommend items to a newly arrived user with no prior …

On Reducing User Interaction Data for Personalization

S Rendle, L Zhang - ACM Transactions on Recommender Systems, 2023 - dl.acm.org
Most recommender systems rely on user interaction data for personalization. Usually, the
recommendation quality improves with more data. In this work, we study the quality …

Deep rating elicitation for new users in collaborative filtering

W Kweon, S Kang, J Hwang, H Yu - Proceedings of The Web …, 2020 - dl.acm.org
Recent recommender systems started to use rating elicitation, which asks new users to rate
a small seed itemset for inferring their preferences, to improve the quality of initial …

Greedy SLIM: A SLIM-Based Approach For Preference Elicitation

C Proissl, A Vatic, H Waldschmidt - arXiv preprint arXiv:2406.06061, 2024 - arxiv.org
Preference elicitation is an active learning approach to tackle the cold-start problem of
recommender systems. Roughly speaking, new users are asked to rate some carefully …

Low-rank kernel matrix approximation using skeletonized interpolation with endo-or exo-vertices

Z Xu, L Cambier, FH Rouet, P L'Eplatennier… - arXiv preprint arXiv …, 2018 - arxiv.org
The efficient compression of kernel matrices, for instance the off-diagonal blocks of
discretized integral equations, is a crucial step in many algorithms. In this paper, we study …

Weighted least-squares approximation with determinantal point processes and generalized volume sampling

A Nouy, B Michel - arXiv preprint arXiv:2312.14057, 2023 - arxiv.org
We consider the problem of approximating a function from $ L^ 2$ by an element of a given
$ m $-dimensional space $ V_m $, associated with some feature map $\varphi $, using …