Accurate bundle matching and generation via multitask learning with partially shared parameters.

How can we recommend existing bundles to users accurately? How can we generate new tailored bundles for users? Recommending a bundle, or a group of various items, has attracted widespread attention in e-commerce owing to the increased satisfaction of both users and providers. Bundle matching and bundle generation are two representative tasks in bundle recommendation. The bundle matching task is to correctly match existing bundles to users while the bundle generation is to generate new bundles that users would prefer. Although many recent works have developed bundle recommendation models, they fail to achieve high accuracy since they do not handle heterogeneous data effectively and do not learn a method for customized bundle generation. In this paper, we propose BundleMage, an accurate approach for bundle matching and generation. BundleMage effectively mixes user preferences of items and bundles using an adaptive gate technique to achieve high accuracy for the bundle matching. BundleMage also generates a personalized bundle by learning a generation module that exploits a user preference and the characteristic of a given incomplete bundle to be completed. BundleMage further improves its performance using multi-task learning with partially shared parameters. Through extensive experiments, we show that BundleMage achieves up to 6.6% higher nDCG in bundle matching and 6.3× higher nDCG in bundle generation than the best competitors. We also provide qualitative analysis that BundleMage effectively generates bundles considering both the tastes of users and the characteristics of target bundles.

Multi-EPL: Accurate multi-source domain adaptation.

Given multiple source datasets with labels, how can we train a target model with no labeled data? Multi-source domain adaptation (MSDA) aims to train a model using multiple source datasets different from a target dataset in the absence of target data labels. MSDA is a crucial problem applicable to many practical cases where labels for the target data are unavailable due to privacy issues. Existing MSDA frameworks are limited since they align data without considering labels of the features of each domain. They also do not fully utilize the target data without labels and rely on limited feature extraction with a single extractor. In this paper, we propose Multi-EPL, a novel method for MSDA. Multi-EPL exploits label-wise moment matching to align the conditional distributions of the features for the labels, uses pseudolabels for the unavailable target labels, and introduces an ensemble of multiple feature extractors for accurate domain adaptation. Extensive experiments show that Multi-EPL provides the state-of-the-art performance for MSDA tasks in both image domains and text domains, improving the accuracy by up to 13.20%.

Unsupervised multi-source domain adaptation with no observable source data.

Given trained models from multiple source domains, how can we predict the labels of unlabeled data in a target domain? Unsupervised multi-source domain adaptation (UMDA) aims for predicting the labels of unlabeled target data by transferring the knowledge of multiple source domains. UMDA is a crucial problem in many real-world scenarios where no labeled target data are available. Previous approaches in UMDA assume that data are observable over all domains. However, source data are not easily accessible due to privacy or confidentiality issues in a lot of practical scenarios, although classifiers learned in source domains are readily available. In this work, we target data-free UMDA where source data are not observable at all, a novel problem that has not been studied before despite being very realistic and crucial. To solve data-free UMDA, we propose DEMS (Data-free Exploitation of Multiple Sources), a novel architecture that adapts target data to source domains without exploiting any source data, and estimates the target labels by exploiting pre-trained source classifiers. Extensive experiments for data-free UMDA on real-world datasets show that DEMS provides the state-of-the-art accuracy which is up to 27.5% point higher than that of the best baseline.

Poly(ethylene oxide)/Ag ions and nanoparticles/1-hexyl-3-methylimidazolium tetrafluoroborate composite membranes with long-term stability for olefin/paraffin separation.

A poly(ethylene oxide)(PEO)/AgBF4/1-hexyl-3-methylimidazolium tetrafluoroborate (HMIM+BF4 -) composite membrane that exhibits long-term stability was prepared for olefin/paraffin separation. The membrane was prepared by simply adding AgBF4 and HMIM+BF4 - to a solution of PEO. Long-term stability testing showed that the separation performance of the membrane is maintained for ≈100 h owing to the Ag NPs formed in the membrane, which are olefin carriers, being stabilized by HMIM+BF4 -. In terms of separation performance, the PEO/AgBF4/HMIM+BF4 - composite membrane exhibited a propylene/propane selectivity of 11.8 and a mixed-gas permeance of 11.3 GPU. We also investigated the factors that determine separation performance by comparison with a PEO/AgBF4/1-butyl-3-methylimidazolium tetrafluoroborate (BMIM+BF4 -) composite membrane. The PEO/AgBF4/HMIM+BF4 - composite membrane was characterized by scanning electron microscopy, FT-IR spectroscopy, ultraviolet-visible spectroscopy, thermogravimetric analysis, and Raman spectroscopy.

Metabolic Profiling of Eccentric Exercise-Induced Muscle Damage in Human Urine.

Skeletal muscle can be ultrastructurally damaged by eccentric exercise, and the damage causes metabolic disruption in muscle. This study aimed to determine changes in the metabolomic patterns in urine and metabolomic markers in muscle damage after eccentric exercise. Five men and 6 women aged 19~23 years performed 30 min of the bench step exercise at 70 steps per min at a determined step height of 110% of the lower leg length, and stepping frequency at 15 cycles per min. 1H NMR spectral analysis was performed in urine collected from all participants before and after eccentric exercise-induced muscle damage conventionally determined using a visual analogue scale (VAS) and maximal voluntary contraction (MVC). Urinary metabolic profiles were built by multivariate analysis of principal component analysis (PCA) and orthogonal partial least square-discriminant analysis (OPLS-DA) using SIMCA-P. From the OPLS-DA, men and women were separated 2 hr after the eccentric exercise and the separated patterns were maintained or clarified until 96 hr after the eccentric exercise. Subsequently, urinary metabolic profiles showed distinct trajectory patterns between men and women. Finally, we found increased urinary metabolites (men: alanine, asparagine, citrate, creatine phosphate, ethanol, formate, glucose, glycine, histidine, and lactate; women: adenine) after the eccentric exercise. These results could contribute to understanding metabolic responses following eccentric exercise-induced muscle damage in humans.