Search

Like common recommender systems, group recommendation usually suffers from popularity bias where popular items are more likely to be suggested and exposed to users over long-tailed ones. The skewed data distribution caused discrimination against a great amount of unpopular items, which will be further intensified during the group decision-making process. Despite previous studies devoted to addressing popularity bias issue in recommendations, rarely have other works concentrated on such problem in group recommender systems. In this paper, we identify the negative impact of item popularity in a causality manner and propose a Popularity Reweighting Framework for Group Recommendation (PopGR). Specifically, a popularity-aware weighting function is adopted to mitigate the bias problem by incorporating the popularity level of items along with their intrinsic characteristics into group modeling. Experiments conducted on two real world benchmark datasets justify the effectiveness of our model to alleviate bias while maintaining reasonable ranking accuracy. [ABSTRACT FROM AUTHOR]

The design of novel materials for sulfur dioxide (SO2) capture and conversion with considerable efficiency under mild conditions is of great significance for human health and environmental protection yet highly challenging. Herein, we report a series of triazine‐based multicomponent metallacages via coordination‐driven self‐assembly of 2,4,6‐tri(4‐pyridyl)‐1,3,5‐triazine, cis‐Pt(PEt3)2(OTf)2 and different tetracarboxylic ligands. As the increase of the length of the tetracarboxylates, the structures of the metallacages change from pyramids to extended octahedrons. Owing to their N‐rich structure, these metallacages are further used for selective SO2 capture, showing good adsorption capacity and remarkable SO2/CO2 selectivity in ambient conditions, suggesting their potential applications toward real flue gas desulfurization. The metallacages are further employed for the conversion of SO2 into value‐added compounds, showing exceptional efficiency even dilute SO2 is used as the reactant. This study represents a type of structure‐tunable triazine‐based metallacages for SO2 capture and conversion, which will pave the way on the applications of metal‐organic complexes for gas adsorption. [ABSTRACT FROM AUTHOR]

Multicomponent metallacages can integrate the functions of their different building blocks to achieve synergetic effects for advanced applications. Herein, based on metal‐coordination‐driven self‐assembly, we report the preparation of a series of isoreticular tetraphenylethylene‐based metallacages, which are well characterized by multinuclear NMR, ESI‐TOF‐MS and single‐crystal X‐ray diffraction techniques. The suitable integration of photosensitizing tetraphenylethylene units as faces and Re catalytic complexes as the pillars into a single metallacage offers a high photocatalytic hydrogen production rate of 1707 μmol g−1 h−1, which is one of the highest values among reported metallacages. Femtosecond transient absorption and DFT calculations reveal that the metallacage can serve as a platform for the precise and organized arrangement of the two building blocks, enabling efficient and directional electron transfer for highly efficient photocatalytic performance. This study provides a general strategy to integrate multifunctional ligands into a certain metallacage to improve the efficiency of photocatalytic hydrogen production, which will guide the future design of metallacages towards photocatalysis. [ABSTRACT FROM AUTHOR]

Multicomponent metallacages can integrate the functions of their different building blocks to achieve synergetic effects for advanced applications. Herein, based on metal‐coordination‐driven self‐assembly, we report the preparation of a series of isoreticular tetraphenylethylene‐based metallacages, which are well characterized by multinuclear NMR, ESI‐TOF‐MS and single‐crystal X‐ray diffraction techniques. The suitable integration of photosensitizing tetraphenylethylene units as faces and Re catalytic complexes as the pillars into a single metallacage offers a high photocatalytic hydrogen production rate of 1707 μmol g−1 h−1, which is one of the highest values among reported metallacages. Femtosecond transient absorption and DFT calculations reveal that the metallacage can serve as a platform for the precise and organized arrangement of the two building blocks, enabling efficient and directional electron transfer for highly efficient photocatalytic performance. This study provides a general strategy to integrate multifunctional ligands into a certain metallacage to improve the efficiency of photocatalytic hydrogen production, which will guide the future design of metallacages towards photocatalysis. [ABSTRACT FROM AUTHOR]

Trip recommendation, which aims to recommend a sequence of point-of-interests (POIs) as a trip to visit, is of great importance to location-based service systems. However, due to data sparsity, existing methods lack the ability to capture complex POI correlations in trips, resulting in limited recommendation performance. In this paper, we propose a graph contextualized trip recommendation model GC-TripRec with adversarial learning to take advantage of graph-based representation learning, so that enhanced trip recommendation can be supported by capturing essential knowledge about complex POI correlations in trips. Specifically, it first models pairwise transition relationships by a global transition graph, upon which global-level POI embedding can be captured by a graph convolution network. We further generate trajectory contextualized POI representation via a trip-level embedding method that compromises transition-based and category-based information of POIs in a single trip. In addition, trip representation is learned through Long Short-Term Memory (LSTM) with an adversarial learning task, such that query representation space would be highly overlapped with trip representation space, enabling getting an excellent trip recommendation system. Comprehensive experiments on four real datasets demonstrate that our proposed GC-TripRec significantly outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Studying the POI recommendation in an online setting becomes meaningful because large volumes of user-POI interactions are generated in a chronological order. Although a few online update strategies have been developed, they cannot be applied in POI recommendation directly because they can hardly capture the long-term user preference only by updating the model with the current data. Besides, some latent POI information is ignored because existing update strategies are designed for traditional recommder systems without considering the addtional factors in POIs. In this paper, we propose an Online Meta-learning POI Recommendation (OMPR) method to solve the problem. To consider the geographical influences among POIs, we use a location-based self-attentive encoder to learn the complex user-POI relations. To capture the drift of user preference in online recommendation, we propose a meta-learning based transfer network to capture the knowledge transfer from both historical and current data. We conduct extensive experiments on two real-world datasets and the results show the superiority of our approaches in online POI recommendation. [ABSTRACT FROM AUTHOR]

The structures of the crosslinks in supramolecular polymer networks play an important role on their properties and functions. Herein, emissive metallacages are used as crosslinks to prepare metallacage‐cored polyurethanes. The mechanical properties including storage modulus, toughness, Young's modulus and breaking strength of polymers are greatly enhanced with the increase of crosslinking densities. Moreover, such polymers not only exhibit good fluorescence in the solid state, but also show self‐healing and shape memory properties owing to the dynamic reversible non‐covalent bonds in their structures. This study not only offers a convenient strategy to prepare metallacage‐crosslinked networks, but also explores their applications as self‐healing and shape memory materials, which will promote the study of metallacage‐cored supramolecular networks as smart materials. [ABSTRACT FROM AUTHOR]

The structures of the crosslinks in supramolecular polymer networks play an important role on their properties and functions. Herein, emissive metallacages are used as crosslinks to prepare metallacage‐cored polyurethanes. The mechanical properties including storage modulus, toughness, Young's modulus and breaking strength of polymers are greatly enhanced with the increase of crosslinking densities. Moreover, such polymers not only exhibit good fluorescence in the solid state, but also show self‐healing and shape memory properties owing to the dynamic reversible non‐covalent bonds in their structures. This study not only offers a convenient strategy to prepare metallacage‐crosslinked networks, but also explores their applications as self‐healing and shape memory materials, which will promote the study of metallacage‐cored supramolecular networks as smart materials. [ABSTRACT FROM AUTHOR]

With the continuous research and development of amidoxime (AO)‐based adsorbents, industrialization production of uranium from seawater gradually becomes a reality. However, the currently available AO‐based adsorbents still suffer from low adsorption rate and poor selectivity. Herein, vertically aligned polyamioxime–graphene oxide (VA‐PG) sheet membrane is fabricated by directional freeze casting. The run‐through microchannels contribute to the free diffusion of uranyl ions (UO22+), leading to the fast adsorption kinetics. Furthermore, partially reduced graphene oxide allows high photothermal conversion efficiency and rapid in‐plane heat transfer, resulting in the fast temperature rise under simulated sunlight irradiation. Because of the endothermic behavior of UO22+, light‐irradiated VA‐PG can simultaneously satisfy the requirements of high adsorption capacity (13.63 mg‐U g‐Ads−1), high adsorption rate (0.43 mg g−1 day−1), and excellent selectivity toward U(VI) over V(V) (U/V = 1.24) in natural seawater, indicating the right direction for a breakthrough in the field of uranium extraction from seawater. [ABSTRACT FROM AUTHOR]

Multi-behavior session-based recommendation aims to predict the next item, such as a location-based service (LBS) or a product, to be interacted by a specific behavior type (e.g., buy or click) in a session involving multiple types of behaviors. State-of-the-art methods generally model multi-behavior dependencies in item-level, but ignore the potential of discovering useful patterns of multi-behavior transition through feature-level representation learning. Besides, sequential and non-sequential patterns should be properly fused in session modeling to capture dynamic interests within the session. To this end, this paper proposes a Graph Neural Network based Hybrid Model GNNH, which enables feature-level deeper representations of multi-behavior interaction sequences for session-based recommendation. Specifically, we first construct multi-relational item graph (MRIG) and feature graph (MRFG) based on session sequences. On top of the MRIG and MRFG, our model takes advantage of GNN to capture item and feature representations, such that global item-to-item and feature-to-feature relations are fully preserved. Afterwards, each multi-behavior session is modeled by a seamless fusion of interacted item and feature representations, where self-attention and mean-pooling are used to obtain sequential and non-sequential patterns simultaneously. Experiments on two real datasets show that the GNNH model significantly outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Travel time estimation (TTE) is an important research topic in many geographic applications for smart city research. However, existing approaches either ignore the impact of transportation modes, or assume the mode information is known for each training trajectory and the query input. In this paper, we propose a multi-task learning model for travel time estimation called MTLM, which recommends the appropriate transportation mode for users, and then estimates the related travel time of the path. It integrates transportation-mode recommendation task and travel time estimation task to capture the mutual influence between them for more accurate TTE results. Furthermore, it captures spatio-temporal dependencies and transportation mode effect by learning effective representations for TTE. It combines the transportation-mode recommendation loss and TTE loss for training. Extensive experiments on real datasets demonstrate the effectiveness of our proposed methods. [ABSTRACT FROM AUTHOR]

Extraordinary electronic and photonic features (e.g., tunable direct bandgap, high ambipolar carrier mobility) render few‐layer black phosphorus (BP) nanosheets/quantum dots an important optoelectronic material. However, most of the BP applied in metal halide perovskite solar cells (PSCs) are produced by sonication‐assisted liquid exfoliation, which inevitably brings inferior electronic properties, thus leading to limited beneficial effects. Furthermore, this study uncovers that the intrinsic instability of BP nanosheets sandwiched between (CsFAMA)Pb(BrI)3 perovskite and spiro‐OMeTAD has a deleterious effect on the performance stabilization of PSCs. To address the above constraints, a feasible strategy herein is developed by introducing high‐quality fluorinated BP (F‐BP) nanosheets synthesized by one‐step electrochemical delamination. In addition to P‐Pb coordination, there is a strong hydrogen bond between F− and MA+/FA+ as well as an ionic bond between F− and Pb2+ for the perovskite/F‐BP interface, thus leading to fewer interfacial traps than perovskite/BP, which is responsible for the highest power conversion efficiency (22.06%) of F‐BP devices. More importantly, F‐BP devices exhibit significantly improved humidity and shelf‐life stabilities due to the excellent ambient stability of F‐BP, resulting from the antioxidation and antihydration behavior of fluorine adatoms. Overall, the findings provide a promising strategy to simultaneously enhance the photovoltaic performance and long‐term stability of BP‐based PSCs. [ABSTRACT FROM AUTHOR]

UiO‐66‐NH2/black phosphorus quantum dots (MOF/BPQDs) heterojunctions are anchored on the carboxyl cellulose nanofiber (CNF) aerogel with high porosity (>98%) to fabricate high‐efficiency uranium adsorbents (BP@CNF‐MOF). CNF aerogels possess abundant carboxyl groups, which can serve as nucleation centers to in situ synthesize UiO‐66‐NH2 with smaller crystal size, high mass loading, and good adhesion. BP@CNF‐MOF demonstrates good mechanical flexibility and minimal MOF loss from the CNF aerogel, both of which result from the mutual physical interactions and entanglements of CNFs as well as strong binding interactions between MOF crystals and CNF aerogel. Owing to the excellent heterogeneous photocatalytic activity of MOF/BPQDs, on one hand, marine bacteria can be effectively destroyed by reactive oxygen species (ROS). On the other hand, the photocatalytic U(VI) reduction to insoluble U(IV) could be facilitated, thereby allowing more binding sites on the MOF crystals for further U(VI) adsorption. Consequently, compared with dark conditions, the adsorption efficiency of the light irradiated BP@CNF‐MOF increases by 55.3%, reaching up to 6.77 mg‐U per g‐Ads after 6 weeks of exposure to natural seawater. The intrinsic instability of BPQDs can be overcome by MOF coating layer simultaneously. The strategy applied in this work could also be applicable to other superior MOF crystals. [ABSTRACT FROM AUTHOR]

This paper describes a type of triazine‐based multicomponent metallacages with tunable structures through changing the chemical structures of the tetracarboxylic building blocks. These metallacages are used for selective SO2 capture and conversion, which will promote the further applications of metallacages for the treatment of harmful gases (e408)..By Ruoqian Zhang; Dingyue Hu; Yu Fu; Qian Feng; Chaoqun Mu; Kai Gao; Heping Ma; Ming Liu and Mingming ZhangReported by Author; Author; Author; Author; Author; Author; Author; Author; Author [Extracted from the article]

Monomolecular VB2 (vitamin B2) was doped into UiO-66 [Zr6O4(OH)4(BDC)12, BDC = 1,4-benzenedicarboxylic acid] via chemical bonds and the obtained VB2@UiO-66 could be used as a heterogeneous photocatalyst. The coordination with UiO-66 was found to be able to positively shift the conduction band of VB2, which thermodynamically precluded the formation of other reactive oxygen species (like O2˙−) except 1O2 under visible light irradiation and led to 1O2 as the only reactive oxygen species for VB2@UiO-66. This result was totally different from that for VB2, which produced various reactive oxygen species, such as O2˙− and 1O2. Due to the fact that 1O2 was the only reactive oxygen species, VB2@UiO-66 displayed excellent photocatalytic selectivity (∼100%) towards benzyl alcohol oxidation. At the same time, chemical bonding with UiO-66 greatly improved the stability of VB2 under visible light. After 5 cycles, the conversion was still 91% and the selectivity was close to 100%. This work offers not only a solution to the poor recyclability, stability and selectivity of VB2 as a photocatalyst but also a new efficient strategy to extend the photocatalytic applications of MOFs by immobilizing common biological antioxidants on their particular sites. [ABSTRACT FROM AUTHOR]

Two transition metal (Co and Ni) ion phosphonates as isostructural organic inorganic hybrids are prepared and investigated in terms of photocatalytic hydrogen evolution from water and CO2 reduction under UV light irradiation. A photocatalytic mechanism of ligand-to-metal charge transfer (LMCT) is proposed. [ABSTRACT FROM AUTHOR]