English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Collaborative filtering models generally perform better than content-basedfiltering models and do not require careful feature engineering. However, inthe cold-start scenario collaborative information may be scarce or evenunavailable, whereas the content information may be abundant, but also noisyand expensive to acquire. Thus, selection of particular features that improvecold-start recommendations becomes an important and non-trivial task. In therecent approach by Nembrini et al., the feature selection is driven by thecorrelational compatibility between collaborative and content-based models. Theproblem is formulated as a Quadratic Unconstrained Binary Optimization (QUBO)which, due to its NP-hard complexity, is solved using Quantum Annealing on aquantum computer provided by D-Wave. Inspired by the reported results, wecontend the idea that current quantum annealers are superior for this problemand instead focus on classical algorithms. In particular, we tackle QUBO viaTTOpt, a recently proposed black-box optimizer based on tensor networks andmultilinear algebra. We show the computational feasibility of this method forlarge problems with thousands of features, and empirically demonstrate that thesolutions found are comparable to the ones obtained with D-Wave across allexamined datasets.

Are Quantum Computers Practical Yet? A Case for Feature Selection in Recommender Systems using Tensor Networks