Are Quantum Computers Practical Yet? A Case for Feature Selection in Recommender Systems using Tensor Networks
This work addresses the cold-start problem in recommender systems for users with limited collaborative data, though it is incremental by proposing a classical alternative to a quantum method.
The paper tackles the problem of feature selection for cold-start recommendations by formulating it as a Quadratic Unconstrained Binary Optimization (QUBO) problem and solves it using TTOpt, a classical tensor network optimizer, showing computational feasibility for thousands of features and solutions comparable to quantum annealing results.
Collaborative filtering models generally perform better than content-based filtering models and do not require careful feature engineering. However, in the cold-start scenario collaborative information may be scarce or even unavailable, whereas the content information may be abundant, but also noisy and expensive to acquire. Thus, selection of particular features that improve cold-start recommendations becomes an important and non-trivial task. In the recent approach by Nembrini et al., the feature selection is driven by the correlational compatibility between collaborative and content-based models. The problem is formulated as a Quadratic Unconstrained Binary Optimization (QUBO) which, due to its NP-hard complexity, is solved using Quantum Annealing on a quantum computer provided by D-Wave. Inspired by the reported results, we contend the idea that current quantum annealers are superior for this problem and instead focus on classical algorithms. In particular, we tackle QUBO via TTOpt, a recently proposed black-box optimizer based on tensor networks and multilinear algebra. We show the computational feasibility of this method for large problems with thousands of features, and empirically demonstrate that the solutions found are comparable to the ones obtained with D-Wave across all examined datasets.