Federated recommender systems are used to address privacy issues in recommendations. Among them, FedVAE extends the representative non-linear recommendation method MultVAE. However, the bottleneck of FedVAE lies in its communication load during training, as the parameter volume of its first and last layers is correlated with the number of items. This leads to significant communication cost during the model's transmission phases (distribution and upload), making FedVAE's implementation extremely challenging. To address these challenges, we propose an Efficient Federated Variational AutoEncoder for collaborative filtering, EFVAE, which core is the Federated Collaborative Importance Sampling (FCIS) method. FCIS reduces communication costs through a client-to-server collaborative sampling mechanism and provides satisfactory recommendation performance through dynamic multi-stage approximation of the decoding distribution. Extensive experiments and analyses on real-world datasets confirm that EFVAE significantly reduces communication costs by up to 94.51% while maintaining the recommendation performance. Moreover, its recommendation performance is better on sparse datasets, with improvements reaching up to 13.79%.

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction data, neglecting to model the diverse matching relationships between users and items behind their interactions, leading to limited performance and weak interpretability. To address this problem, we propose a Dual Disentangled Variational AutoEncoder (DualVAE) for collaborative recommendation, which combines disentangled representation learning with variational inference to facilitate the generation of implicit interaction data. Specifically, we first implement the disentangling concept by unifying an attention-aware dual disentanglement and disentangled variational autoencoder to infer the disentangled latent representations of users and items. Further, to encourage the correspondence and independence of disentangled representations of users and items, we design a neighborhood-enhanced representation constraint with a customized contrastive mechanism to improve the representation quality. Extensive experiments on three real-world benchmarks show that our proposed model significantly outperforms several recent state-of-the-art baselines. Further empirical experimental results also illustrate the interpretability of the disentangled representations learned by DualVAE.

Session-based recommendation (SBR) aims to predict the anonymous user's next-click items by modeling the short-term sequence pattern. As most existing SBR models generally generate item representations based only on information propagation over the short sequence while ignoring additional valuable knowledge, their expressive abilities are somewhat limited by data sparsity caused by short sequence. Though there have been some attempts on utilizing items' attributes, they basically embed attributes into items directly, ignoring the fact that 1) there is no contextual relationship among attributes; and 2) users have varying levels of attention to different attributes, which still leads to unsatisfactory performance. To tackle the issues, we propose a novel Attribute-enhanced Dual Channel Representation Learning (ADRL) model for SBR, in which we independently model session representations in attribute-related pattern and sequence-related pattern. Specifically, we learn session representations with sequence patterns from the session graph, and we further design an frequency-driven attribute aggregator to generate the attribute-related session representations within a session. The proposed attribute aggregator is plug-and-play, as it can be coupled with most existing SBR models. Extensive experiments on three real-world public datasets demonstrate the superiority of the proposed ADRL over several state-of-the-art baselines, as well as the effectiveness and efficiency of our attribute aggregator module.

Session-based recommendation (SBR) has received increasing attention to predict the next item via extracting and integrating both global and local item-item relationships. However, there still exist some deficiencies in current works when capturing these two kinds of relationships. For global item-item relationships, the global graph constructed by most SBR is a pseudo-global graph, which may cause redundant mining of sequence relationships. For local item-item relationships, conventional SBR only mines the sequence patterns while ignoring the feature patterns, which may introduce noise when learning users' interests. To address these problems, we propose a novel Knowledge-enhanced Multi-View Graph Neural Network (KMVG) by constructing three views, namely knowledge view, session view, and pairwise view. Specifically, benefiting from the rich semantic information in the knowledge graph (KG), we build a genuine global graph that is sequence-independent based on KG to mine the global item-item relationships in the knowledge view. Then, a session view is utilized to capture the contextual transitions among items as the sequence patterns of local item-item relationships, and a pairwise view is used to explore the feature commonality within a session as the feature patterns of the local item-item relationships. Extensive experiments on three real-world public datasets demonstrate the superiority of KMVG, showing that it outperforms the state-of-the-art baselines. Further analysis also reveals the effectiveness of KMVG in exploiting the item-item relationships under multiple views.

Next-basket recommendation (NBR) is a type of recommendation that aims to recommend a set of items to users according to their historical basket sequences. Existing NBR methods suffer from two limitations: (1) overlooking low-level item correlations, which results in coarse-grained item representation; and (2) failing to consider spurious interests in repeated behaviors, leading to suboptimal user interest learning. To address these limitations, we propose a novel solution named Multi-view Multi-aspect Neural Recommendation (MMNR) for NBR, which first normalizes the interactions from both the user-side and item-side, respectively, aiming to remove the spurious interests, and utilizes them as weights for items from different views to construct differentiated representations for each interaction item, enabling comprehensive user interest learning. Then, to capture low-level item correlations, MMNR models different aspects of items to obtain disentangled representations of items, thereby fully capturing multiple user interests. Extensive experiments on real-world datasets demonstrate the effectiveness of MMNR, showing that it consistently outperforms several state-of-the-art NBR methods.

Due to the success of graph convolutional networks (GCNs) in effectively extracting features in non-Euclidean spaces, GCNs has become the rising star in implicit collaborative filtering. Existing works, while encouraging, typically adopt simple aggregation operation on the user-item bipartite graph to model user and item representations, but neglect to mine the sufficient dependencies between nodes, e.g., the relationships between users/items and their neighbors (or congeners), resulting in inadequate graph representation learning. To address these problems, we propose a novel Multi-Dependency Graph Collaborative Filtering (MDGCF) model, which mines the neighborhood- and homogeneous-level dependencies to enhance the representation power of graph-based CF models. Specifically, for neighborhood-level dependencies, we explicitly consider both popularity score and preference correlation by designing a joint neighborhood-level dependency weight, based on which we construct a neighborhood-level dependencies graph to capture higher-order interaction features. Besides, by adaptively mining the homogeneous-level dependencies among users and items, we construct two homogeneous graphs, based on which we further aggregate features from homogeneous users and items to supplement their representations, respectively. Extensive experiments on three real-world benchmark datasets demonstrate the effectiveness of the proposed MDGCF. Further experiments reveal that our model can capture rich dependencies between nodes for explaining user behaviors.

The string similarity search is core functionality in a range of applications, including data cleaning, near-duplicate object detection, and data integration. We study the problem of threshold similarity search with the edit distance, where given a set of strings, a threshold$k$, and a query string$q$, we aim to find all strings in the set whose edit distances to$q$are no larger than$k$. Extensive studies have been proposed for the threshold similarity search problem with the edit distance. However, they suffer from a huge space consumption issue when achieving only an acceptable efficiency, especially for long strings. In this paper, we propose a simple yet small index, called minIL, to eliminate this issue. First, we adopt a minhash family to capture pivot characters and to construct sketch representations for strings. Second, we develop a multi-level inverted index to search sketches with a low space consumption. Finally, we apply a novel learned index technique on top of the index that further improves the query efficiency. Extensive experiments on real-world datasets offer insight into the performance of our method and show that it substantially reduces the index size, and is capable of outperforming the baseline approaches.

The explosive growth of e-commerce and online service has led to the development of recommender system. Aiming to provide a list of items to meet a user’s personalized need by analyzing his/her interaction 1 history, recommender system has been widely studied in academic and industrial communities. Different from conventional recommender systems, sequential recommender systems attempt to capture the pattern of users’ sequential behaviors and the evolution of users’ preferences. Most of the existing sequential recommendation models only focus on user interaction sequence, but neglect item interaction sequence. An item interaction sequence also contains rich contextual information for capturing the item’s dynamic characteristic, since an item’s dynamic characteristic can be reflected by the users who interact with it in a period. Furthermore, existing dual sequential models use the same method to handle the user interaction sequence and item interaction sequence, and do not consider their different characteristics. Hence, we propose a novel D ouble A ttention C onvolution N eural N etwork (DACNN) , which incorporates user interaction sequence and item interaction sequence into an integrated neural network framework. DACNN leverages the strength of attention mechanism to capture the temporary suitability and adopts CNN to extract local sequential features. Experimental evaluations on the real datasets show that DACNN outperforms the baseline approaches.

Reinforcement learning-based portfolio management has recently attracted extensive attention. However, deep reinforcement learning methods are unexplainable and considered to be potentially risky, difficult to be trusted and regulated by users. To address these problems, we propose an eXplainable reinforcement learning framework for Portfolio Management, named XPM, which is efficient, concise, and can provide faithful explanations for network outputs. Specifically, we first design a policy network for portfolio management, which uses temporal convolutional network (TCN) to extract temporal features of multiple time series in portfolio. Then, we employ global average pooling (GAP) and a fully connected layer to integrate the global feature maps to handle asset correlations. Finally, we utilize softmax to determine the output portfolio weights. To assemble explainability into our model, we employ an explainable artificial intelligence method, class activation mapping (CAM), to explain the network outputs, which computes an activation map for an asset of interest. The map highlights the important assets and time intervals in the input state. In this way, end users can understand which part of the portfolio's recent price movements makes the network decision to invest in the target asset. Experimental results show that XPM outperforms the current state-of-the-art portfolio management methods in NASDAQ and NYSE markets, and can provide faithful and informative explanations to end users.

Streaming spatial-textual data that contains geographic and textual information, e.g., geo-tagged tweets, has an unprecedented increase in amount. As one of the basic operations, the continuous spatial-textual queries that retrieve real-time results continuously on large-scale spatial-textual streams call for means of efficient distributed processing. However, existing proposals either are spatialaware only, or superficially exploit textual information for pruning. We propose a distributed system, called HASTE, for hybrid and adaptive processing on streaming spatial-textual data. The novelty lies on three aspects: (1) We propose a novel method to reduce the workload beforehand by dividing objects and queries into mutually exclusive types; (2) We develop a novel load partitioning strategy and a novel cost model that consider both spatial and textual properties; (3) We design a multi-level load adjustment strategy that adaptively copes with different degrees of load imbalance. We report on extensive experiments with real-world data that offer insight into the performance of the solution, and show that the solution is capable of outperforming the state-of-the-art proposals.

Many navigation applications take natural language speech as input, which avoids typing in words with their hands and decreases the occurrence of traffic accidents. We propose the SpearkNav navigation system that enables users to describe intended routes via speech and supports clue-based route retrieval. SpeakNav includes a route description language understanding model for determining POIs and distances along expected routes, and it includes an efficient algorithm to compute desired routes. In addition, SpeakNav supports basic POI and location search and location-based route navigation. We demonstrate how SpeakNav accurately recognizes users' intentions and recommends appropriate routes in real application scenarios.

Data sparsity is a challenge problem that most modern recommender systems are confronted with. By leveraging the knowledge from relevant domains, the cross-domain recommendation technique can be an effective way of alleviating the data sparsity problem. In this paper, we propose a novel Bi-directional Transfer learning method for cross-domain recommendation by using Graph Collaborative Filtering network as the base model (BiTGCF). BiTGCF not only exploits the high-order connectivity in user-item graph of single domain through a novel feature propagation layer, but also realizes the two-way transfer of knowledge across two domains by using the common user as the bridge. Moreover, distinct from previous cross-domain collaborative filtering methods, BiTGCF fuses users' common features and domain-specific features during transfer. Experimental results on four couple benchmark datasets verify the effectiveness of BiTGCF over state-of-the-art models in terms of bi-directional cross domain recommendation.

The set similarity join (SSJ) is core functionality in a range of applications, including data cleaning, near-duplicate object detection, and data integration. Threshold-based SSJ queries return all pairs of sets with similarity no smaller than a given threshold. As results, and their utility, are very sensitive to the choice of threshold value, it is a problem that it is difficult to choose such an appropriate value. Doing so requires prior knowledge of the data, which users often do not have. To avoid this problem, we propose a solution to the top-k overlap set similarity join (TkOSSJ) that returns k pairs of sets with the highest overlap similarities. The state-of-the-art solution disregards the effect of the so-called step size, which is the number of elements accessed in each iteration of the algorithm. This affects its performance negatively. To address this issue, we first propose an algorithm that uses a fixed step size, thus taking advantage of the benefits of a large step size, and then we present an adaptive step size algorithm that is capable of automatically adjusting the step size, thus reducing redundant computations. An extensive empirical study offers insight into the new algorithms and indicates that they are capable of outperforming the state-of-the-art method on real, large-scale data sets.

In Pickup-and-Delivery problems (PDP), mobile workers are employed to pick up and deliver items with the goal of reducing travel and fuel consumption. Unlike most existing efforts that focus on finding a schedule that enables the delivery of as many items as possible at the lowest cost, we consider trichromatic (worker-item-task) utility that encompasses worker reliability, item quality, and task profitability. Moreover, we allow customers to specify keywords for desired items when they submit tasks, which may result in multiple pickup options, thus further increasing the difficulty of the problem. Specifically, we formulate the problem of Online Trichromatic Pickup and Delivery Scheduling (OTPD) that aims to find optimal delivery schedules with highest overall utility. In order to quickly respond to submitted tasks, we propose a greedy solution that finds the schedule with the highest utility-cost ratio. Next, we introduce a skyline kinetic tree-based solution that materializes intermediate results to improve the result quality. Finally, we propose a density-based grouping solution that partitions streaming tasks and efficiently assigns them to the workers with high overall utility. Extensive experiments with real and synthetic data offer evidence that the proposed solutions excel over baselines with respect to both effectiveness and efficiency.

With the proliferation of geo-textual objects on the web, extensive efforts have been devoted to improving the efficiency of top-k spatial keyword queries in different settings. However, comparatively much less work has been reported on enhancing the quality and usability of such queries. In this context, we propose means of enhancing the usability of a top-k group spatial keyword query, where a group of users aim to find k objects that contain given query keywords and are nearest to the users. Specifically, when users receive the result of such a query, they may find that one or more objects that they expect to be in the result are in fact missing, and they may wonder why. To address this situation, we develop a so-called why-notquery that is able to minimally modifythe original query into a query that returns the expected, but missing, objects, in addition to other objects. Specifically, we formalize the why-not query in relation to the top-k group spatial keyword query, called the Why-not Group Spatial Keyword Query (WGSK) that is able to provide a group of users with a more satisfactory query result. We propose a three-phase framework for efficiently computing the WGSK. The first phase substantially reduces the search space for the subsequent phases by retrieving a set of objects that may affect the ranking of the user-expected objects. The second phase provides an incremental sampling algorithm that generates candidate weightings of more promising queries. The third phase determines the penalty of each refined query and returns the querywith minimal penalty, i.e., the minimally modified query. Extensive experiments with real and synthetic data offer evidence that the proposed solution excels over baselines with respect to both effectiveness and efficiency.

The explosive growth of e-commerce has led to the development of the recommendation system. The recommendation system aims to provide a set of items that meet users’ personalized needs through analyzing users’ consumption records. However, the timeliness of purchasing data and the implicity of feedback data pose severe challenges for the existing recommendation methods. To alleviate these challenges, we exploit the user’s consumption records from the perspectives of user and item, by modeling the data on both item and user level, where the item-level value reflects the grade of item, and the user-level value reflects the user’s purchase intention. In this article, we collect the description information and the reviews of the items from public websites, then adopt sentiment analysis techniques to model the similarities on user level and item level, respectively. In particular, we extend the traditional latent factor model and propose two novel methods— I tem L evel Similarity M atrix F actorization (ILMF) and U ser L evel Similarity M atrix F actorization (ULMF)—by introducing two novel similarity measure methods. In ILMF and ULMF, the consistency between latent factors and explicit aspects is naturally incorporated into learning latent factors of the users and items, such that we can predict the users’ preferences on different items more accurately. Moreover, we propose I tem- U ser L evel Similarity M atrix F actorization (IULMF), which combines these two methods to study their contributions on the final performance. Experimental evaluations on the real datasets show that our methods outperform the baseline approaches in terms of both the precision and NDCG.

Detecting rumor source in social networks is one of the key issues for defeating rumors automatically. Although many efforts have been devoted to defeating online rumors, most of them are proposed based an assumption that the underlying propagation model is known in advance. However, this assumption may lead to impracticability on real data, since it is usually difficult to acquire the actual underlying propagation model. Some attempts are developed by using label propagation to avoid the limitation caused by lack of prior knowledge on the underlying propagation model. Nonetheless, they still suffer from the shortcoming that the node label is simply an integer which may restrict the prediction precision. In this paper, we propose a deep learning based model, namely GCNSI (Graph Convolutional Networks based Source Identification), to locate multiple rumor sources without prior knowledge of underlying propagation model. By adopting spectral domain convolution, we build node representation by utilizing its multi-order neighbors information such that the prediction precision on the sources is improved. We conduct experiments on several real datasets and the results demonstrate that our model outperforms state-of-the-art model.

Financial portfolio management is the process of periodically reallocating a fund into different financial investment products, with the goal of achieving the maximum profits. While conventional financial machine learning methods try to predict the price trends, reinforcement learning based portfolio management methods makes trading decisions according to the price changes directly. However, existing reinforcement learning based methods are limited in extracting the price change information at single-scale level, which makes their performance still not satisfactory. In this paper, inspired by the Inception network that has achieved great success in computer vision and can extract multi-scale features simultaneously, we propose a novel Ensemble of Identical Independent Inception (EI$^3$) convolutional neural network, with the objective of addressing the limitation of existing reinforcement learning based portfolio management methods. With EI$^3$, multiple assets can be processed independently while sharing the same network parameters. Moreover, price movement information for each product can be extracted at multiple scales via wide network and then aggregated to make trading decision. Based on EI$^3$, we further propose a recurrent reinforcement learning framework to provide a deep machine learning solution for the portfolio management problem. Comprehensive experiments on the cryptocurrency datasets demonstrate the superiority of our method over existing competitors, in both upswing and downswing environments.

With the proliferation of geo-textual objects on the web, extensive efforts have been devoted to improving the efficiency of top-k spatial keyword queries in different settings. However, comparatively much less work has been reported on enhancing the quality and usability of such queries. In this context, we propose means of enhancing the usability of a top-k group spatial keyword query, where a group of users aim to find k objects that contain given query keywords and are nearest to the users. Specifically, when users receive the result of such a query, they may find that one or more objects that they expect to be in the result are in fact missing, and they may wonder why. To address this situation, we develop a so-called why-not query that is able to minimally modify the original query into a query that returns the expected, but missing, objects, in addition to other objects. Specifically, we formalize the why-not query in relation to the top-k group spatial keyword query, called the Why-not Group Spatial Keyword Query (WGSK) that is able to provide a group of users with a more satisfactory query result. We propose a three-phase framework for efficiently computing he WGSK. Extensive experiments with real and synthetic data offer evidence that the proposed solution excels over baselines with respect to both effectiveness and efficiency.

With the advances in geo-positioning technologies and location-based services, it is nowadays quite common for road networks to have textual contents on the vertices. Previous work on identifying an optimal route that covers a sequence of query keywords has been studied in recent years. However, in many practical scenarios, an optimal route might not always be desirable. Therefore, in this paper, we investigate the problem of clue-based route search (CRS), which allows a user to provide clues on keywords and spatial relationships. First, we propose a greedy algorithm and a dynamic programming algorithm as baselines. To improve efficiency, we develop a branch-and-bound algorithm that prunes unnecessary vertices in query processing. In order to quickly locate candidate, we propose an AB-tree that stores both the distance and keyword information in tree structure. To further reduce the index size, we construct a PB-tree by utilizing the virtue of 2-hop label index to pinpoint the candidate. Extensive experiments are conducted and verify the superiority of our algorithms and index structures.

With the advances in geo-positioning technologies and location-based services, it is nowadays quite common for road networks to have textual contents on the vertices. Previous work on identifying an optimal route that covers a sequence of query keywords has been studied in recent years. However, in many practical scenarios, an optimal route might not always be desirable. For example, a personalized route query is issued by providing some clues that describe the spatial context between PoIs along the route, where the result can be far from the optimal one. Therefore, in this paper, we investigate the problem of clue-based route search (CRS), which allows a user to provide clues on keywords and spatial relationships. First, we propose a greedy algorithm and a dynamic programming algorithm as baselines. To improve efficiency, we develop a branch-and-bound algorithm that prunes unnecessary vertices in query processing. In order to quickly locate candidate, we propose an AB-tree that stores both the distance and keyword information in tree structure. To further reduce the index size, we construct a PB-tree by utilizing the virtue of 2-hop label index to pinpoint the candidate. Extensive experiments are conducted and verify the superiority of our algorithms and index structures.

It is nowadays quite common for road networks to have textual contents on the vertices, which describe auxiliary information (e.g., business, traffic, etc.) associated with the vertex. In such road networks, which are modelled as weighted undirected graphs, each vertex is associated with one or more keywords, and each edge is assigned with a weight, which can be its physical length or travelling time. In this paper, we study the problem of keyword-aware continuous k nearest neighbour (KCkNN) search on road networks, which computes the k nearest vertices that contain the query keywords issued by a moving object and maintains the results continuously as the object is moving on the road network. Reducing the query processing costs in terms of computation and communication has attracted considerable attention in the database community with interesting techniques proposed. This paper proposes a framework, called a Labelling AppRoach for Continuous kNN query (LARC), on road networks to cope with KCkNN query efficiently. First we build a pivot-based reverse label index and a keyword-based pivot tree index to improve the efficiency of keyword-aware k nearest neighbour (KkNN) search by avoiding massive network traversals and sequential probe of keywords. To reduce the frequency of unnecessary result updates, we develop the concepts of dominance interval and region on road network, which share the similar intuition with safe region for processing continuous queries in Euclidean space but are more complicated and thus require more dedicated design. For high frequency keywords, we resolve the dominance interval when the query results changed. In addition, a path-based dominance updating approach is proposed to compute the dominance region efficiently when the query keywords are of low frequency. We conduct extensive experiments by comparing our algorithms with the state-of-the-art methods on real data sets. The empirical observations have verified the superiority of our proposed solution in all aspects of index size, communication cost and computation time.

Expert finding has become a hot topic along with the flourishing of social networks, such as micro-blogging services like Twitter. Finding experts inTwitteris an important problem because tweets from experts are valuable sources that carry rich information (e.g., trends) in various domains. However, previous methods cannot be directly applied toTwitterexpert finding problem. Recently, several attempts use the relations among users andTwitter Lists for expert finding. Nevertheless, these approaches only partially utilize such relations. To this end, we develop a probabilistic method to jointly exploit three types of relations (i.e.,followerrelation,user-listrelation, andlist-listrelation) for finding experts. Specifically, we propose aSemi-SupervisedGraph-basedRanking approach ($\sf{SSGR}$) to offline calculate theglobal authorityof users. In$\sf{SSGR}$, we employ a normalized Laplacian regularization term to jointly explore the three relations, which is subject to the supervised information derived from Twitter crowds. We then online compute thelocal relevancebetween users and the given query. By leveraging theglobal authorityandlocal relevanceof users, we rank all of users and find top-N users with highest ranking scores. Experiments on real-world data demonstrate the effectiveness of our proposed approach fortopic-specificexpert finding inTwitter.