Search

A preliminary version of this article appeared in the proceedings of CIKM 2020 [10]. In this extension, we (1) propose another interest extractor, i.e., dynamic routing, in the implicit interest mining module, and another type of disagreement regularization, i.e., output disagreement regularization, in our interest-aware, diversity promoting loss; (2) investigate the performance of our multi-interest, diversified, sequential recommendation model with different interest extractors in implicit interest mining, i.e., multi-head attention vs. dynamic routing; (3) investigate the performance of multi-interest, diversified, sequential recommendation with various latent interests numbers; (4) explore the influence of the parameter λ on the performance of multi-interest, diversified, sequential recommendation; (5) investigate the performance of multiinterest, diversified, sequential recommendation with different types of disagreement regularization; (6) investigate the impact of maximum entropy regularization on the performance of multi-interest, diversified, sequential recommendation; (7) provide a case study to show the recommendations generated by multi-interest, diversified, sequential recommendation; (8) analyze the computational complexity of the baseline model as well as our proposal; and (9) survey more related work and conduct a more detailed analysis of the approach and experimental results. [ABSTRACT FROM AUTHOR]

We propose a Joint Neural Collaborative Filtering (J-NCF) method for recommender systems. The J-NCF model applies a joint neural network that couples deep feature learning and deep interaction modeling with a rating matrix. Deep feature learning extracts feature representations of users and items with a deep learning architecture based on a user-item rating matrix. Deep interaction modeling captures non-linear user-item interactions with a deep neural network using the feature representations generated by the deep feature learning process as input. J-NCF enables the deep feature learning and deep interaction modeling processes to optimize each other through joint training, which leads to improved recommendation performance. In addition, we design a new loss function for optimization that takes both implicit and explicit feedback, pointwise and pair-wise loss into account. Experiments on several real-world datasets show significant improvements of J-NCF over state-of-the-art methods, with improvements of up to 8.24% on the MovieLens 100K dataset, 10.81% on the MovieLens 1M dataset, and 10.21% on the Amazon Movies dataset in terms of HR@10. NDCG@10 improvements are 12.42%, 14.24%, and 15.06%, respectively. We also conduct experiments to evaluate the scalability and sensitivity of J-NCF. Our experiments show that the J-NCF model has a competitive recommendation performance with inactive users and different degrees of data sparsity when compared to state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

In this paper, the content of rockery protection was discussed through the analysis of a series of documents such as the convention, declaration, and regulations concerning heritage protection in accordance with the principles of authenticity and integrity. Through the analysis of the influence factors of the rockery and its environment, it is proposed that the rockery protection should strengthen environmental protection on the basis of the protection of the body of a rockery. From the perspectives of structure, skill, materials and function, the contents of the rockery protection and the human settlement environment where the rockery is located, the external environment and internal environment of the rockery space were analyzed, and the contents of the rockery protection were preliminarily proposed. [ABSTRACT FROM AUTHOR]

Query completion approaches assist searchers in formulating queries with few keystrokes when using an information retrieval system to address their information needs, which help users benefit from avoiding spelling mistakes and from producing clear query formulations, etc. Previous work on query completion algorithms returns a ranked list of queries to the users mostly based on the overall observed search popularity of query candidates in the whole query logs. However, the query search popularity could be changed over time, i.e., it's time-aware. Thus, these ranking approaches based on the overall search popularity could not work very well and users may fail to find an acceptable query in the returned list, resulting in a limited search satisfaction. Hence, this paper proposes a Learning-based Personalized Query Ranking approach, i.e., LQR, where the features on the observed and predicted search popularity both in the whole logs and the recent period are exploited. Taking a pair-wise learning scenario, this paper presents a method for generating a ranked list of query candidates, and then reranks the candidates by the similarity to current search context. The experimental results show the proposed approach outperforms the baseline in terms of Mean Reciprocal Rank (MRR), reporting an average MRR improvement of 7% against the baseline. [ABSTRACT FROM AUTHOR]

Background: Oxygen consumption reflects multiple processes in pancreatic islets including mechanisms contributing to insulin secretion, oxidative stress and viability, providing an important readout in studies of islet function, islet viability and drug testing. Due to the scarcity, heterogeneity, and intrinsic kinetic properties of individual islets, it would be of great benefit to detect oxygen consumption by single islets. We present a novel method we have developed to image oxygen in single islets. Methodology/Principal Findings: Using a microfluidics system, individual islets and a fluorescent oxygen-sensitive dye were encased within a thin alginate polymer layer. Insulin secretion by the encapsulated islets was normal. Fluorescent signal from the encased dye, detected using a standard inverted fluorescence microscope and digital camera, was stable and proportional to the amount of oxygen in the media. When integrated into a perifusion system, the sensing system detected changes in response to metabolic substrates, mitochondrial poisons, and induced-oscillations. Glucose responses averaged 30.1±7.1% of the response to a metabolic inhibitor (cyanide), increases were observed in all cases (n = 6), and the system was able to resolve changes in oxygen consumption that had a period greater than 0.5 minutes. The sensing system operated similarly from 2-48 hours following encapsulation, and viability and function of the islets were not significantly affected by the encapsulation process. Conclusions/Significance: An oxygen-dependent dye situated around and within a pancreatic islet encapsulated by a thin layer of alginate was sensitive to changes in oxygen consumption, and was not harmful to the function or viability of islets over the course of two days. The microcapsule-based sensing method is particularly suited to assessing the effects of compounds (dose responses and time courses) and chronic changes occurring over the course of days. The approach should be applicable to other cell types and dyes sensitive to other biologically important molecules. [ABSTRACT FROM AUTHOR]

Supramolecular hydrogel microspheres are hydrogel particles formed by the self-assembly of hydrogelators in water, through non-covalent interactions. In this paper, we provide a novel strategy to prepare supramolecular hydrogel microspheres with diameters ranging from 15 to 105 microns by using microfluidics. Since the gelation temperature is ca.64 °C, the aqueous solution containing the hydrogelator was initially set at 70 °C so the liquid mixture can be pumped into the microfluidic device. The hydrogelator solution then pinches off into uniform micron size droplets at the narrow orifice of the microfluidic device. While traveling downstream in the microchannel, the self-assembly process occurs inside the droplets and the droplets solidify into microsphere gels when the temperature drops to ca.64 °C and below. Optical and scanning electron microscopy (SEM) demonstrate that compact, entangled, round, cage-like aggregates of hydrogelator were formed within the supramolecular hydrogel microsphere, in contrast to loose and less compact aggregates within bulk hydrogel. Thermal analysis (DSC) indicates that supramolecular hydrogel microspheres are more thermally stable and can immobilize more water molecules, owing to the compact entangled three-dimensional network structures. This observation is of particular importance for potential drug delivery and biomaterials applications. [ABSTRACT FROM AUTHOR]

1,3:2,4-di- p-methylbenzylidene sorbitol (MDBS) is a small organic molecule that is capable of inducing self-assembly in a wide variety of organic solvents and of forming organogels. In this paper, we present a novel approach to tune the network architectures of organogels by utilizing geometric confinement while varying the gelator concentration. Self-assembly of MDBS in propylene carbonate (PC) is investigated in a series of microchannels with widths varying from 20 to 80 μm and the gelator concentration varying from 2 to 7 wt %. We demonstrate by optical microscopy and scanning electron microscopy (SEM) that a transition from fibrillar structure to sheaflike spherulite structure occurs when (a) the channel width is increased for fixed gelator concentrations and (b) gelator concentration is increased for fixed channel widths. A phase diagram is built based on these observations. Polarized microscopy and transmission electron microscopy (TEM) images are also obtained for organogel under unconfined condition to display the spherulite structures viewed under different length scales. The thermal properties of the organogel are measured by differential scanning calorimetry (DSC) to verify the structural difference obtained under confined and unconfined conditions and the structure stability. Our results provide a novel strategy to control the topological structure of self-assembled systems and to modify their thermal properties via geometric confinement. [ABSTRACT FROM AUTHOR]

Abstract  Ionically cross-linked polyampholytic hydrogels were synthesized by redox copolymerization of acrylamide and an ionic complex of (N,N-diethylamino)ethyl methacrylate and acrylic acid (designated as PADA hydrogel). The swelling behavior of the hydrogels in water indicated that a minimal equilibrium swelling ratio is found when the molar ratio of anionic/cationic monomers was 1.55. In NaCl solution, the hydrogels exhibited the typical swelling behavior of conventional polyampholytic gels. Their equilibrium swelling ratios increased with an increase in the NaCl concentration. In solutions of multivalent ions (CaCl2 and trisodium citrate solutions), the equilibrium swelling ratios of the hydrogels increased first and were then followed by a decrease with an increase in salt concentration. Interestingly, an unexpected abrupt swelling phenomenon was observed when the fully swollen hydrogels in salt solution were transmitted to pure water. The unique swelling behavior of PADA hydrogels depends not only on the molar ratio of the anionic/cationic monomers but also on the valency of the ions. [ABSTRACT FROM AUTHOR]

Session-based recommendation (SBR), which mainly relies on a user’s limited interactions with items to generate recommendations, is a widely investigated task. Existing methods often apply RNNs or GNNs to model user’s sequential behavior or transition relationship between items to capture her current preference. For training such models, the supervision signals are merely generated from the sequential interactions inside a session, neglecting the correlations of different sessions, which we argue can provide additional supervisions for learning the item representations. Moreover, previous methods mainly adopt the cross-entropy loss for training, where the user’s ground truth preference distribution towards items is regarded as a one-hot vector of the target item, easily making the network over-confident and leading to a serious overfitting problem. Thus, in this article, we propose a Collaborative Graph Learning (CGL) approach for session-based recommendation. CGL first applies the Gated Graph Neural Networks (GGNNs) to learn item embeddings and then is trained by considering both the main supervision as well as the self-supervision signals simultaneously. The main supervisions are produced by the sequential order while the self-supervisions are derived from the global graph constructed by all sessions. In addition, to prevent overfitting, we propose a Target-aware Label Confusion (TLC) learning method in the main supervised component. Extensive experiments are conducted on three publicly available datasets, i.e., Retailrocket, Diginetica, and Gowalla. The experimental results show that CGL can outperform the state-of-the-art baselines in terms of Recall and MRR. [ABSTRACT FROM AUTHOR]

Session-based recommendation aims to generate recommendations merely based on the ongoing session, which is a challenging task. Previous methods mainly focus on modeling the sequential signals or the transition relations between items in the current session using RNNs or GNNs to identify user’s intent for recommendation. Such models generally ignore the dynamic connections between the local and global item transition patterns, although the global information is taken into consideration by exploiting the global-level pair-wise item transitions. Moreover, existing methods that mainly adopt the crossentropy loss with softmax generally face a serious over-fitting problem, harming the recommendation accuracy. Thus, in this article, we propose a Graph Co-Attentive Recommendation Machine (GCARM) for session-based recommendation. In detail, we first design a Graph Co-Attention Network (GCAT) to consider the dynamic correlations between the local and global neighbors of each node during the information propagation. Then, the item-level dynamic connections between the output of the local and global graphs are modeled to generate the final item representations. After that, we produce the prediction scores and design a Max Cross-Entropy (MCE) loss to prevent over-fitting. Extensive experiments are conducted on three benchmark datasets, i.e., Diginetica, Gowalla, and Yoochoose. The experimental results show that GCARM can achieve the state-of-the-art performance in terms of Recall and MRR, especially on boosting the ranking of the target item. [ABSTRACT FROM AUTHOR]

The storage of living cells is the major challenge for cell research and cell treatment. Here, we introduced a novel supramolecular gel cryopreservation system which was prepared in the microchannel, and the supramolecular gel (BDTC) was self-assembled by gelator Boc-O-dodecyl-l-tyrosine (BDT). This cryopreservation system could obviously minimize the cell injury because the BDTC supramolecular gel had a more compact three-dimensional network structure when the BDT gelator self-assembled in the confined space of microchannel. This compact structure could confine the growth of the ice crystal, reduce the change rate of cell volumes and osmotic shock, decrease the freezing point of the cryopreservation system, and possess better protection capability. Furthermore, the results of functionality assessments showed that the thawed cells could grow and proliferate well and remain the same growth trend of the fresh cells after the RSC96 cells flowed out from the microchannel. This novel method has potential to be used for the cryopreservation of cells, cell therapy, and tissue engineering. [ABSTRACT FROM AUTHOR]