arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.04490cs.IRcs.LG
收藏

量子计算机实用吗?推荐系统中基于张量网络的特征选择

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

Skolkovo Institute of Science and Technology(斯科尔科沃科技学院);IE University(IE大学);Artificial Intelligence Research Institute(人工智能研究院)

Artyom Nikitin, Andrei Chertkov, Rafael Ballester-Ripoll, Ivan Oseledets, Evgeny Frolov

摘要:

协同过滤模型通常比基于内容的过滤模型性能更好,并且不需要仔细的特征工程。然而,在冷启动场景中,协作信息可能是稀缺的或甚至不可用的,而内容信息可能是丰富的,但是也是嘈杂的并且获取起来昂贵。因此,选择特定的功能,提高冷启动建议成为一个重要的和不平凡的任务。在Nembini等人最近的方法中,特征选择由协作模型和基于内容的模型之间的相关兼容性驱动。该问题被公式化为二次无约束二进制优化(QUBO),由于其NP-困难的复杂性,在D-Wave提供的量子计算机上使用量子退火来解决。受报告结果的启发,我们认为当前的量子退火机在这个问题上更优越,而是专注于经典算法。特别是,我们通过TTOpt来解决QUBO问题,TTOpt是最近提出的一种基于张量网络和多线性代数的黑盒优化器。我们展示了这种方法对于具有数千个特征的大型问题的计算可行性,并根据经验证明,在所有检查的数据集上,找到的解决方案与使用D-Wave获得的解决方案相当。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑