In recommender systems, multi-behavior methods have demonstrated significant effectiveness in addressing issues such as data sparsity—challenges commonly encountered by traditional single-behavior recommendation methods. These methods typically infer user preferences from various auxiliary behaviors and apply them to recommendations for the target behavior. However, existing methods face challenges in uncovering the interaction patterns for different behaviors from multi-behavior implicit feedback, as users exhibit varying preference strengths for different items across behaviors. To address this issue, this paper introduces a novel approach, Decision-Aware Preference Modeling (DAPM), for multi-behavior recommendation. We first construct a behavior-agnostic graph to learn comprehensive representations that are not affected by behavior factors, complementing the behavior-specific representations. Subsequently, we introduce an innovative contrastive learning paradigm that emphasizes inter-behavior consistency and intra-behavior uniformity to alleviate the “false repulsion” problem in traditional contrastive learning. Furthermore, we propose a multi-behavior hinge loss with boundary constraints to explicitly model users' decision boundaries across different behaviors, thereby enhancing the model’s ability to accurately capture users' inconsistent preference intensities. Extensive experiments on three real-world datasets demonstrate the consistent improvements achieved by DAPM over thirteen state-of-the-art baselines. We release our code at https://github.com/Breeze-del/DAPM.

Top-N recommendation systems are recognized as highly effective for delivering personalized services that cater to the varied interests of users. Nonetheless, current state-of-the-art (SOTA) analyses reveal a marked variability in their performance across users with differing levels of activity, which substantially undermines the quality of personalized recommendation services. Prevailing research tends to overlook this discrepancy, often presuming a uniform probability distribution in user preferences and employing a static model (such as a single latent vector) for user representation. This oversimplification impedes the adaptability of existing models to accommodate the spectrum of user activity levels. In our research, we introduce the variational kernel density estimation (VKDE) approach, an innovative nonparametric method designed to accurately capture the unique preference distributions of individual users. The VKDE framework integrates multiple local distributions to construct a comprehensive global preference profile for each user. We have developed a novel variational kernel function that delineates user-specific interests and constructs each local distribution accordingly. Additionally, we present a tailored sampling strategy that simplifies the complexity of the training process while preserving the efficacy of the recommendations. Empirical evaluations conducted on four widely recognized public datasets demonstrate that our VKDE model achieves superior performance over the SOTA alternatives, significantly enhancing accuracy for users with a broad range of activity levels.

A modern service model known as the “hub-oriented” model has emerged with the development of mobility services. This model allows users to request vehicles from multiple companies (agents) simultaneously through a unified entry (a ‘hub’). In contrast to conventional services, the “hub-oriented” model emphasizes pricing competition. To address this scenario, an agent should consider its competitors when developing its pricing strategy. In this paper, we introduce DRLPG, a mixed opponent-aware pricing method, which consists of two main components: the two-stage guarantor and the end-to-end deep reinforcement learning (DRL) module, as well as interaction mechanisms. In the guarantor, we design a prediction-decision framework. Specifically, we propose a new objective function for the spatiotemporal neural network in the prediction stage and utilize a traditional reinforcement learning method in the decision stage, respectively. In the end-to-end DRL framework, we explore the adoption of conventional DRL in the “hub-oriented” scenario. Finally, a meta-decider and an experience-sharing mechanism are proposed to combine both methods and leverage their advantages. We conduct extensive experiments on real data, and DRLPG achieves an average improvement of 99.9% and 61.1% in the peak and low peak periods, respectively. Our results demonstrate the effectiveness of our approach compared to the baseline.

Due to the easy access, implicit feedback is often used for recommender systems. Compared with point-wise learning and pair-wise learning methods, list-wise rank learning methods have superior performance for top- \(N\) recommendation. Recent solutions, especially the list-wise methods, simply treat all interacted items of a user as equally important positives and annotate all no-interaction items of a user as negatives. For the list-wise approaches, we argue that this annotation scheme of implicit feedback is over-simplified due to the sparsity and missing fine-grained labels of the feedback data. To overcome this issue, we revisit the so-called positive and negative samples. First, considering the loss function of list-wise ranking, we analyze the impact of false positives and negatives theoretically. Second, based on the observation, we propose a self-adjusting credibility weight mechanism to re-weigh the positive samples and exploit the higher-order relation based on item–item matrix to sample the critical negative samples. In order to prevent the introduction of noise, we design a pruning strategy for critical negatives. Besides, to combine the reconstruction loss function for the positive samples and critical negative samples, we develop a simple yet effective VAEs framework with linear structure, which abandons the complex non-linear structure. Extensive experiments are conducted on six public real-world datasets. The results demonstrate that, our VAE* outperforms other VAE-based models by a large margin. Besides, we also verify the effect of denoising positives and exploring critical negatives by ablation study.

Recommendation systems in auction platforms like eBay function differently in comparison to those found in traditional trading platforms. The bidding process involves multiple users competing for a product, with the highest bidder winning the item. As a result, each transaction is independent and characterized by varying transaction prices. The individual nature of auction items means that users cannot purchase identical items, adding to the uniqueness of the purchasing history. Bidders in auction systems rely on their judgment to determine the value of a product, as bidding prices reflect preferences rather than cost-free actions like clicking or collecting. Conventional methodologies that heavily rely on user-item purchase history are ill-suited to handle these unique and extreme product features. Unfortunately, prior recommendation approaches have failed to give due attention to the contextual intricacies of auction items, thereby missing out on the full potential of the invaluable bidding record at hand.

Socially tenuous groups (or simply tenuous groups) in a social network/graph refer to subgraphs with few social interactions and weak relationships among members. However, existing studies on tenuous group queries do not consider the user profiles (keywords) of the members whereas in many social network applications, e.g., finding reviewers for paper selection and recommending seed users in social advertising, keywords also need to be considered. Thus, in this paper, we investigate the problem of keywords-based socially tenous group (KTG) queries. A KTG query is to find top N tenuous groups in which the members of each group jointly cover the most number of query keywords. To address the KTG problem, we first propose two exact algorithms, namely KTG-VKC and KTG-VKC-DEG, which give priority to the valid keyword coverage and the combination of valid keyword coverage and degree, respectively, to select members to form a feasible group by adopting a branch and bound (BB) strategy. Moreover, we propose keyword pruning and k-line filtering to accelerate the algorithms. To yield diversified KTG results, we also study the problem of diversified keywords-based socially tenous group (DKTG) queries. To deal with the DKTG problem, we propose a DKTG-Greedy algorithm by exploiting a greedy heuristic in combination with KTG-VKC-DEG. Furthermore, we design two alternative indexes, namely NL and NLRNL, to efficiently check whether the social distance of any two members is greater than the social constraint k in the above algorithms. We conduct extensive experiments using real datasets to validate our ideas and evaluate the proposed algorithms. Experimental results show that the NLRNL index achieves a better performance than the NL index.

Geo-social groupqueries, which return a social cohesive user group with a spatial constraint, have receive significant research interests due to their promising applications for group-based activity planning and scheduling in location-based social networks (LBSNs). However, existing studies on geo-social group queries mostly assume the users are stationary whereas in realistic LBSN application scenarios all users may continuously move over time. Thus, in this paper, we investigate the problem ofcontinuousgeo-socialgroupsmonitoring(CGSGM) over moving users. A challenge in answering CGSGM queries over moving users is how to efficiently update geo-social groups when users are continuously moving. To address the CGSGM problem, we first propose a baseline algorithm, namelyBaseline-BB, which recomputes the new geo-social groups from scratch at each time instance by utilizing a branch and bound (BB) strategy. To improve the inefficiency of BB, we explore a new strategy, called common neighbor or neighbor expanding (CNNE), which expands the common neighbors of edges or the neighbors of users in intermediate groups to quickly produce the valid group combinations. Accordingly, another baseline algorithm, namelyBaseline-CNNE, is proposed. As these baseline algorithms do not maintain intermediate results to facilitate further query processing, we develop an incremental algorithm, calledincremental monitoring algorithm (IMA), which maintains the support, common neighbors and the neighbors of current users when exploring possible user groups for further updates and query processing. Since IMA requires many times of truss decomposition when processing mutiple-users updates, we propose an improved incremental algorithm, calledimproved incremental monitoring algorithm (IIMA), which performs truss decompostion only once. Moreover, we design algorithms for handling the social changes that result in insertion/deletion of some edges in the social network. Owing to the challenge in setting, an appropriate monitoring distance, we further study the top$N$CGSGM problem, which finds top$N$result groups at each time instance. Finally, we conduct extensive experiments using four real datasets to validate our ideas and evaluate the proposed algorithms.

In this paper, we study a novel variant of geo-social group queries, namely, keyword-based geo-social group (KGSG) queries. Motivated by group-based activity planning, KGSG ensures that the attendees have a good social relationship, are close enough to the activity location, and are interested in the activity. Efficient processing of the KGSG query is very challenging as the problem is NP-hard. To address the challenge, we first propose two R-tree based algorithms, namely Distance Ordering based (Baseline) and Breadth Distance Ordering with Neighbor Expanding (BDONE). To further improve these two R-tree based algorithms, we propose a new keyword-aware social spatial index, called SIR-tree, which incorporates spatial, social and keyword information into an R-tree. The novelty of SIR-tree lies in the idea of projecting the social relationships of an LBSN on the spatial layer which also maintains the users keyword information, to facilitate efficient KGSG query processing. Accordingly, we develop an efficient algorithm, called KGSG by SIR-tree Acceleration (KGSG-SIR), which exploits SIR-tree to accelerate query processing of KGSG. We conduct an extensive performance evaluation using four real datasets to validate our ideas and the proposed algorithms. The experimental result shows that the KGSG-SIR algorithm outperforms the two algorithms significantly.

Recently a lot of research works have focused on geo-social group queries for group-based activity planning and scheduling in location-based social networks (LBSNs), which return a social cohesive user group with a spatial constraint. However, existing studies on geo-social group queries assume the users are stationary whereas in real LBSN applications all users may continuously move over time. Thus, in this paper we in-vestigate the problem of continuous geo-social groups monitoring (CGSGM) over moving users. A challenge in answering CGSGM queries over moving users is how to efficiently update geo-social groups when users are continuously moving. To address the CGSGM problem, we first propose a baseline algorithm, namely Baseline-BB, which recomputes the new geo-social groups from scratch at each time instance by utilizing a branch and bound (BB) strategy. To improve the inefficiency of BB, we propose a new strategy, called common neighbor or neighbor expanding (CNNE), which expands the common neighbors of edges or the neighbors of users in intermediate groups to quickly produce the valid group combinations. Based on CNNE, we propose another baseline algorithm, namely Baseline-CNNE. As these baseline algorithms do not maintain any intermediate results to facilitate further query processing, we develop an incremental algorithm, called incremental monitoring algorithm (IMA), which maintains the support, common neighbors and the neighbors of current users when exploring possible user groups for further updates and query processing. Finally, we conduct extensive experiments using three real datasets to validate our ideas and evaluate the proposed algorithms,

Abstract The optimal sequenced route (OSR) query, as a popular problem in route planning for smart cities, searches for a minimum-distance route passing through several POIs in a specific order from a starting position. In reality, POIs are usually rated, which helps users in making decisions. Existing OSR queries neglect the fact that the POIs in the same category could have different scores, which may affect users’ route choices. In this paper, we study a novel variant of OSR query, namely Rating Constrained Optimal Sequenced Route query (RCOSR), in which the rating score of each POI in the optimal sequenced route should exceed the query threshold. To efficiently process RCOSR queries, we first extend the existing TD-OSR algorithm to propose a baseline method, called MTDOSR. To tackle the shortcomings of MTDOSR, we try to design a new RCOSR algorithm, namely Optimal Subroute Expansion (OSE) Algorithm. To enhance the OSE algorithm, we propose a Reference Node Inverted Index (RNII) to accelerate the distance computation of POI pairs in OSE and quickly retrieve the POIs of each category. To make full use of the OSE and RNII, we further propose a new efficient RCOSR algorithm, called Recurrent Optimal Subroute Expansion (ROSE), which recurrently utilizes OSE to compute the current optimal route as the guiding path and update the distance of POI pairs to guide the expansion. Then, we extend our techniques to handle a variation of RCOSR query, namely RCkOSR query. The experimental results demonstrate that the proposed algorithm significantly outperforms the existing approaches.

Hashing is a practical approach for the approximate nearest neighbor search. Deep hashing methods, which train deep networks to generate compact and similarity-preserving binary codes for entities (e.g. images), have received lots of attention in the information retrieval community. A representative stream of deep hashing methods is triplet-based hashing that learns hashing models from triplets of data. The existing triplet-based hashing methods only consider triplets that are in the form of$(q,q^{+},q^{-})$, where$q$and$q^{+}$are in the same class and$q$and$q^{-}$are in different classes. However, the number of possible triplets is approximately the cube of training examples, triplets used in the existing methods are only a small fraction of all possible triplets. This motivates us to develop a new triplet-based hashing method that adopts many more triplets in training phase. We propose Deep Listwise Triplet Hashing (DLTH) that introduces more triplets into batch-based training and a novel listwise triplet loss to capture the relative similarity in new triplets. This method has a pipeline of two steps. In Step 1, we propose a novel way to generate triplets from the soft class labels obtained by knowledge distillation module, where the triplets in the form of$(q,q^{+},q^{-})$are a subset of the newly obtained triplets. In Step 2, we develop a novel listwise triplet loss to train the hashing network, which seeks to capture the relative similarity between images in triplets according to soft labels. We conduct comprehensive image retrieval experiments on four benchmark datasets. The experimental results show that the proposed method has superior performances over state-of-the-art baselines.

Abstract Motivated by location-based social networks which allow people to access location-based services as a group, we study a novel variant of optimal sequenced route (OSR) queries, optimal sequenced route for group meetup (OSR-G) queries. OSR-G query aims to find the optimal meeting POI (point of interest) such that the maximum users’ route distance to the meeting POI is minimized after each user visits a number of POIs of specific categories (e.g., gas stations, restaurants, and shopping malls) in a particular order. To process OSR-G queries, we first propose an OSR-Based (OSRB) algorithm as our baseline, which examines every POI in the meeting category and utilizes existing OSR (called E-OSR) algorithm to compute the optimal route for each user to the meeting POI. To address the shortcomings (i.e., requiring to examine every POI in the meeting category) of OSRB, we propose an upper bound based filtering algorithm, called circle filtering (CF) algorithm, which exploits the circle property to filter the unpromising meeting POIs. In addition, we propose a lower bound based pruning (LBP) algorithm, namely LBP-SP which exploits a shortest path lower bound to prune the unqualified meeting POIs to reduce the search space. Furthermore, we develop an approximate algorithm, namely APS, to accelerate OSR-G queries with a good approximation ratio. Finally the experimental results show that both CF and LBP-SP outperform the OSRB algorithm and have high pruning rates. Moreover, the proposed approximate algorithm runs faster than the exact OSR-G algorithms and has a good approximation ratio.

This paper focuses on generating multi-hop reasoning questions from the raw text in a low resource circumstance.Such questions have to be syntactically valid and need to logically correlate with the answers by deducing over multiple relations on several sentences in the text.Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text.Since the labeled data is limited and insufficient for training, we propose to learn the model with the help of a large scale of unlabeled data that is much easier to obtain.Such data contains rich expressive forms of the questions with structural patterns on syntax and semantics.These patterns can be estimated by the neural hidden semi-Markov model using latent variables.With latent patterns as a prior, we can regularize the generation model and produce the optimal results.Experimental results on the HotpotQA data set demonstrate the effectiveness of our model.Moreover, we apply the generated results to the task of machine reading comprehension and achieve significant performance improvements.

Terahertz (THz) band communication has been widely studied to meet the future demand for ultra-high capacity. In addition, multi-input multi-output (MIMO) technique and non-orthogonal multiple access (NOMA) technique with multiantenna also enable the network to serve more users. In this paper, we study the maximization of energy efficiency (EE) problem in THz-NOMA-MIMO systems for the first time. And the original optimization problem is divided into user clustering and hybrid precoding. Based on channel correlation characteristics, a fast convergence scheme for user clustering using enhanced K-means machine learning algorithm is proposed. Considering the power consumption and complexity, the hybrid precoding scheme based on the sub-connection structure is adopted. The simulation results show that the proposed scheme can achieve faster convergence and higher EE.

Terahertz (THz) band communication has been widely studied to meet the future demand for ultra-high capacity. In addition, multi-input multi-output (MIMO) technique and non-orthogonal multiple access (NOMA) technique with multi-antenna also enable the network to carry more users and provide multiplexing gain. In this paper, we study the maximization of energy efficiency (EE) problem in THz-NOMA-MIMO systems for the first time. And the original optimization problem is divided into user clustering, hybrid precoding and power optimization. Based on channel correlation characteristics, a fast convergence scheme for user clustering in THz-NOMA-MIMO system using enhanced K-means machine learning algorithm is proposed. Considering the power consumption and implementation complexity, the hybrid precoding scheme based on the sub-connection structure is adopted. Considering the fronthaul link capacity constraint, we design a distributed alternating direction method of multipliers (ADMM) algorithm for power allocation to maximize the EE of THz-NOMA cache-enabled system with imperfect successive interference cancellation (SIC). The simulation results show that the proposed user clustering scheme can achieve faster convergence and higher EE, the design of the hybrid precoding of the sub-connection structure can achieve lower power consumption and power optimization can achieve a higher EE for the THz cache-enabled network.

NOMA is a key technology for future wireless communication, which can improve the spectral efficiency (SE) of mobile network. In this paper, a subchannel assignment algorithm is applied to maximize the energy efficiency of downlink heterogeneous NOMA network. Different from previous works, the subchannel assignment problems and power allocation problem are formulated as non-convex problem, then we transform the original problems to convex optimization problems and solve it using difference of convex functions (DC) programming. The simulation results confirm that the applied scheme not only enhance the sum rate of heterogeneous NOMA network but also energy efficiency (EE) of small cell base station (SBS).

Millimeter wave (mmWave) communication technology has become an attractive solution to meet exponential growth demand for mobile data services. In this paper, we propose a deep neural networks (DNN) based algorithm for user association and power optimization problem in mmWave heterogeneous network on the basis of gradient iterative algorithm. We jointly design the user association and power optimization to maximize energy efficiency (EE) utilizing Lagrange dual decomposition and then approximate it by DNN models. In addition, an asynchronous distributed DNN based scheme is proposed, which divides the large network model into small distributed networks for distributed data processing on each small base station side to reduce computational time. Simulation results show that the proposed scheme can achieve a high EE with low computation time.

Learning user’s preference from check-in data is important for POI recommendation. Yet, a user usually has visited some POIs while most of POIs are unvisited (i.e., negative samples). To leverage these “no-behavior” POIs, a typical approach is pairwise ranking, which constructs ranking pairs for the user and POIs. Although this approach is generally effective, the negative samples in ranking pairs are obtained randomly, which may fail to leverage “critical” negative samples in the model training. On the other hand, previous studies also utilized geographical feature to improve the recommendation quality. Nevertheless, most of previous works did not exploit geographical information comprehensively, which may also affect the performance. To alleviate these issues, we propose a geographical information based adversarial learning model (Geo-ALM), which can be viewed as a fusion of geographic features and generative adversarial networks. Its core idea is to learn the discriminator and generator interactively, by exploiting two granularity of geographic features (i.e., region and POI features). Experimental results show that Geo- ALM can achieve competitive performance, compared to several state-of-the-arts.