Indirect Neighbors Research Articles

EPT-GCN: Edge propagation-based time-aware graph convolution network for POI recommendation

In location-based social networks (LBSNs), point-of-interest (POI) recommendation systems help users identify unvisited POIs by filtering large amounts of information. Accurate POI recommendations can effectively improve user satisfaction and save time in finding POIs. In recent years, the graph convolution network (GCN) technique, which enhances the representational ability of neural networks by learning the embeddings of users and items, has been widely adopted in recommendation systems to improve accuracy. Combining GCN with various information, such as time and geographical information, can further improve recommendation performance. However, existing GCN-based techniques simply adopt time information by modeling users’ check-in sequences, which is insufficient and ignores users’ time-based high-order connectivity. Note that time-based high-order connectivity refers to the relationship between indirect neighbors with similar preferences in the same time slot. In this paper, we propose a new time-aware GCN model to extract rich collaborative signals contained in time information. Our work is the first to divide user check-ins into multiple subgraphs, i.e., time slots, based on time information. We further propose an edge propagation module to adjust edge affiliation, where edges represent check-ins, to propagate user’s time-based preference to multiple time slots. The propagation module is based on an unsupervised learning algorithm and does not require additional ground-truth labels. Experimental results confirm that our method outperforms state-of-the-art GCN models in all baselines, improving Recall@5 from 0.0803 to 0.0874 (8.84%) on the Gowalla dataset and from 0.0360 to 0.0388 (7.78%) on the New York dataset. The proposed subgraph mining technique and novel edge-based propagation module have high scalability and can be applied to other subgraph construction models.

Global Graph Attention Embedding Network for Relation Prediction in Knowledge Graphs.

The incompleteness of knowledge graphs triggers considerable research interest in relation prediction. As the key to predicting relations among entities, many efforts have been devoted to learning the embeddings of entities and relations by incorporating a variety of neighbors' information which includes not only the information from direct outgoing and incoming neighbors but also the ones from the indirect neighbors on the multihop paths. However, previous models usually consider entity paths of limited length or ignore sequential information of the paths. Either simplification will make the model lack a global understanding of knowledge graphs and may result in the loss of important and indispensable information. In this article, we propose a novel global graph attention embedding network (GGAE) for relation prediction by combining global information from both direct neighbors and multihop neighbors. Concretely, given a knowledge graph, we first introduce the path construction algorithms to obtain meaningful paths, then design path modeling methods to capture the potential long-distance sequential information in the multihop paths, final propose an entity graph attention and a relation graph attention mechanisms to obtain entity embeddings and relation embeddings. Moreover, an entity graph attention mechanism is proposed to calculate the entity embeddings by aggregating direct incoming and outgoing neighbors from: 1) an original knowledge graph with the original entity and relation embeddings and 2) a new knowledge graph constructed by the paths whose embeddings are updated by path modeling methods. for each relation, we construct a new graph with related entities and present a relation graph attention to learn the features. Therefore, our model can encapsulate the information from different distance neighbors, and enable the embeddings of entities and relations to better capture all-sided semantic information. The experimental results on benchmark datasets verify the superiority of our model over the state-of-the-art ones.

Latent neighborhood-based heterogeneous graph representation

Graph, as a powerful data structure, has shown superior capability on modeling complex systems. Since real-world objects and their interactions are often multi-modal and multi-typed, compared with traditional homogeneous graphs, heterogeneous graphs can represent real-world objects more effectively. Meanwhile, rich semantic information brings great challenges for learning heterogeneous graph representation (HGR). Most existing HGR methods are based on the concept of meta-path, which is constructed based on direct neighbors and define composite semantic relations in heterogeneous graph. However, when the direct neighbor information is inadequate, which always happens due to insufficient observation, the quality of meta-paths cannot be guaranteed. Therefore, we propose a novel HGR framework based on latent direct neighbors. Specifically, random walks are first utilized to discover the potential candidates from indirect neighbors. Then HodgeRank is introduced to determine the latent direct neighbors according to their importance to the target. After that, neighborhood relationships are augmented with the selected latent direct neighbors, and the adjacency tensor of the heterogeneous graph is refactored correspondingly. Finally, Graph Transformer Network is adopted to construct semantic meta-paths automatically and generate HGR. Numerical experiments on different real-world heterogeneous networks show that our new approach can produce more meta-path instances and introduce more complex and diverse semantic information, and consequently achieves more accurate predictions compared with several state-of-the-art baselines.

Research on Product Design Strategy Based on User Preference and Machine Learning Intelligent Recommendation

In the machine learning model, intelligent recommendation system can select valuable information from a lot of data to help users find the products or services they need, which has been more and more widely used in recent years. However, there are still many problems in machine learning recommender systems, such as data sparsity, natural noise, and cold start, which leads to the fact that machine learning recommender systems cannot obtain accurate user preferences. When a project is rated, the quality of the recommendation is greatly affected. In order to solve the problem that the existing recommendation algorithms have poor recommendation results in sparse data sets, this paper proposes a machine learning method for recommendation rating prediction based on user interest concept lattice. Firstly, the nearest neighbors are divided into direct nearest neighbors and indirect nearest neighbors by user interest concept lattice. Then, different methods are used to calculate the similarity between the direct “nearest neighbor” and the target user, and the similarity between the indirect “nearest neighbor” and the target user. Finally, the invisible item score of the target user is calculated by the similarity value. Experiments are carried out on real data sets, and the experimental results show that the CFCNN-CL algorithm and RRP-UI CL algorithm proposed in this paper have high recommendation accuracy and still have good performance in the case of sparse data.

Iterative rating prediction for neighborhood-based collaborative filtering

This paper investigates the issue of rating prediction for neighborhood-based collaborative filtering in recommendation systems. A novel rating prediction algorithm, called iterative rating prediction (IRP), is proposed for neighborhood-based collaborative filtering. The main idea behind IRP is neighborhood propagation. To predict ratings of items for target users, IRP relies on not only the rating information of direct neighbors but also that of indirect neighbors with different propagation depth. To implement the idea, IRP iteratively updates the ratings of items for users. The efficiency of the proposed method is examined through extensive experiments. Experimental results demonstrate the superior performance of our method, especially on small-scaled and sparse datasets.

VN-NDP: A Neighbor Discovery Protocol Based on Virtual Nodes in Mobile WSNs.

As an indispensable part of Internet of Things (IoT), wireless sensor networks (WSNs) are more and more widely used with the rapid development of IoT. The neighbor discovery protocols are the premise of communication between nodes and networking in energy-limited self-organizing wireless networks, and play an important role in WSNs. Because the node energy is limited, neighbor discovery must operate in an energy-efficient manner, that is, under the condition of a given energy budget, the neighbor discovery performance should be as good as possible, such that the discovery latency would be as small as possible and the discovered neighbor percentage as large as possible. The indirect neighbor discovery mainly uses the information of the neighbors that have been found by a pairwise discovery method to more efficiently make a re-planning of the discovery wake-up schedules of the original pairwise neighbor discovery, thereby improving the discovery energy efficiency. The current indirect neighbor discovery methods are mainly divided into two categories: one involves removing the inefficient active slots in the original discovery wake-up schedules, and the other involves adding some efficient active slots. However, the two categories of methods have their own limitations. The former does not consider that this removal operation destroys the integrity of the original discovery wake-up schedules and hence the possibility of discovering new neighbors is reduced, which adversely affects the discovered neighbor percentage. For the latter category, there are still inefficient active slots that were not removed in the re-planned wake-up schedules. The motivation of this paper is to combine the advantages of these two types of indirect neighbor discovery methods, that is, to combine the addition of efficient active slots and the removal of inefficient active slots. To achieve this goal, this paper proposes, for the first time, the concept of virtual nodes in neighbor discovery to maximize the integrity of the original wake-up schedules and achieve the goals of adding efficient active slots and removing inefficient active slots. Specifically, a virtual node is a collaborative group that is formed by nodes within a small range. The nodes in a collaborative group share responsibility for the activating task of one member node, and the combination of these nodes’ wake-up schedules forms the full wake-up schedule of a node that only uses a pairwise method. In addition, this paper proposes a set of efficient group management mechanisms, and the key steps affecting energy efficiency are analyzed theoretically to obtain the energy-optimal parameters. The extended simulation experiments in multiple scenarios show that, compared with other methods, our neighbor discovery protocol based on virtual nodes (VN-NDP) has a significant improvement in average discovery delay and discovered neighbor percentage performance at a given energy budget. Compared with the typical indirect neighbor discovery algorithm EQS, a neighbor discovery with extended quorum system, our proposed VN-NDP method reduces the average discovery delay by up to and increases the discovered neighbor percentage by up to .

Proposing a novel method for improving the performance of collaborative filtering systems regarding the priority of similar users

Recommender systems (RS) are an efficient and useful tool for personalizing services and providing efficient recommendations to users in different applications. One of the most successful techniques used in Recommender Systems is Collaborative Filtering (CF) which uses the rating matrix to find users with similar interests as the active user. The issue which usually arises with this method is the sparsity of the rating matrix which affects the process of finding similar users and the quality of the recommendations greatly. In this paper, a new method has been provided to increase the efficiency of the system against sparse data domains. The basis of the proposed method is extracting preference patterns from the rating matrix in the way that for each active user, a three-level tree of neighboring users is constructed. The active user is situated in the root of the tree, direct neighbors of the active user in the second level and indirect neighbors of the active user are situated in the third level. Then the similarity level of the active user with its direct and indirect neighbors is calculated. Finally the calculated similarity value is used in the process of predicting the ratings. This factor affects the quality of the ratings given by the neighbors. Results of the experiments on Movielens and Jester datasets indicate that in most cases, the proposed method provides better results than other widely utilized methods.

Diversified recommendation method combining topic model and random walk

As one of the most widely used algorithms in recommendation field, collaborative filtering (CF) predicts the unknown rating of items based on similar neighbors. Although many CF-based recommendation methods have been proposed, there still be room for improvement. Firstly, the data sparsity problem still remains a big challenge for CF algorithms to find similar neighbors. Secondly, there are many redundant similar items in the recommendation list generated by traditional CF algorithms, which cannot meet the user wide interest. Therefore, we propose a diversified recommendation method combining topic model and random walk. A weighted random walk model is presented to find all direct and indirect similar neighbors on the sparse data, improving the accuracy of rating prediction. By taking both users’ behavior data and items’ lags into account, we give a diversity measurement method based on the topic distribution of items discovered by Linked-LDA model. Furthermore, a diversified ranking algorithm is developed to balance the accuracy and diversity of recommendation results. We compare our method with six other recommendation methods on a real-world dataset. Experimental results show that our method outperforms the other methods and achieves the best personalized recommendation effect.

Asymmetric evaluation promotes cooperation in network population

The evolution of cooperation remains a fundamental challenge in human society. Many previous studies investigated these questions via spatial reciprocity, where players obtain their payoffs by interacting with their direct neighbors. It has also been verified that environmental factors can influence the evolution of cooperation theoretically and empirically. In reality, however, individuals may have the limit knowledge about their indirect neighbors. Inspired by this fact, we consider an asymmetric fitness calculation mechanism, which only integrates the environment factors into the focal player, to explore the evolution of cooperation. Here, the environmental factor is defined as the average payoff of all individual neighbors, which is regulated by a tunable parameter u. Through numerical simulation, we find that, compared with the traditional version (u=0), that the cooperation level can be greatly enhanced when u is positive. Interestingly, the larger the value of u, the higher the level of cooperation. Finally, to explore the generality of this finding, we have tested the results on different topologies.

Detecting communities in social networks using label propagation with information entropy

Community detection has become an important and effective methodology to understand the structure and function of real world networks. The label propagation algorithm (LPA) is a near-linear time algorithm used to detect non-overlapping community. However, it merely considers the direct neighbor relationship. In this paper, we propose an algorithm to consider information entropy as the measurement of the relationship between direct neighbors and indirect neighbors. In a label update, we proposed a new belonging coefficient to describe the weight of the label. With the belonging coefficient no less than a threshold each node can keep one or more labels to constitute an overlapping community. Experimental results on both real-world and benchmark networks show that our algorithm also possesses high accuracy on detecting community structure in networks.

Four-king chess with dice is neither unrealistic nor messed up

AbstractKauṭilya’smaṇḍalamodel has intrigued indologists and political scientists for some time. It deals with friendship and enmity between countries that are direct or indirect neighbours. (Ghosh; 1936) suggests a close relationship between this model and Indian four-king chess. We try to corroborate his claim by presenting a stylized game-theory model of both Indian four-king chess andKauṭilya’smaṇḍalatheory. Within that game model, we can deal withKauṭilya’s conjecture according to which an enemy’s enemy is likely to be one’s friend. Arguably, this conjecture is reflected in the ally structure of four-king chess. We also comment on the widespread disapproval of dice in (four-king) chess.

Collective prediction based on community structure

Abstract Collective prediction algorithms have been used to improve performances when network structures are involved in prediction tasks. The training dataset of such tasks often contain information of content, links and labels, while the testing dataset have only content and link information. Conventional collective prediction algorithms conduct predictions based on the content of a node and the information of its direct neighbors with a base classifier. However, the information of some direct neighbor nodes may be not consistent with the target one. In addition, the information of indirect neighbors can be helpful when that of direct neighbors is scant. In this paper, instead of using information of direct neighbors, we propose to apply community structures in networks to prediction tasks. A community detection method is aggregated into the collective prediction process to improve prediction performance. Experimental results show that the proposed algorithm outperforms a number of standard prediction algorithms specially under conditions that labeled training dataset are limited.

Missing gene identification using functional coherence scores.

Reconstructing metabolic and signaling pathways is an effective way of interpreting a genome sequence. A challenge in a pathway reconstruction is that often genes in a pathway cannot be easily found, reflecting current imperfect information of the target organism. In this work, we developed a new method for finding missing genes, which integrates multiple features, including gene expression, phylogenetic profile, and function association scores. Particularly, for considering function association between candidate genes and neighboring proteins to the target missing gene in the network, we used Co-occurrence Association Score (CAS) and PubMed Association Score (PAS), which are designed for capturing functional coherence of proteins. We showed that adding CAS and PAS substantially improve the accuracy of identifying missing genes in the yeast enzyme-enzyme network compared to the cases when only the conventional features, gene expression, phylogenetic profile, were used. Finally, it was also demonstrated that the accuracy improves by considering indirect neighbors to the target enzyme position in the network using a proper network-topology-based weighting scheme.

A Degree-Distance-Based Connections Model with Negative and Positive Externalities

We develop a modification of the connections model by Jackson and Wolinsky (1996) that takes into account negative externalities arising from the connectivity of direct and indirect neighbors, thus combining aspects of the connections model and the co-author model. We consider a general functional form for agents’ utility that incorporates both the effects of distance and of neighbors’ degree. Consequently, we introduce a framework that can be seen as a degree-distance-based connections model with both negative and positive externalities. Our analysis shows how the introduction of negative externalities modifies certain results about stability and efficiency compared to the original connections model. In particular, we see the emergence of new stable structures, such as a star with links between peripheral nodes. We also identify structures, for example, certain disconnected networks, that are efficient in our model but which could not be efficient in the original connections model. While our results are proved for the general utility function, some of them are illustrated by using a specific functional form of the degree-distance-based utility.

A Degree‐Distance‐Based Connections Model with Negative and Positive Externalities

AbstractWe develop a modification of the connections model by Jackson and Wolinsky that takes into account negative externalities arising from the connectivity of direct and indirect neighbors, thus combining aspects of the connections model and the coauthor model. We consider a general functional form for agents' utility that incorporates both the effects of distance and of neighbors' degree. Consequently, we introduce a framework that can be seen as a degree‐distance‐based connections model with both negative and positive externalities. Our analysis shows how the introduction of negative externalities modifies certain results about stability and efficiency compared to the original connections model. In particular, we see the emergence of new stable structures, such as a star with links between peripheral nodes. We also identify structures, for example, certain disconnected networks, that are efficient in our model but which could not be efficient in the original connections model. While our results are proved for the general utility function, some of them are illustrated by using a specific functional form of the degree‐distance‐based utility.

Generic Neighbor Discovery Accelerations in Mobile Applications

As a supporting primitive of many mobile applications, neighbor discovery identifies nearby devices so that they can exchange information and collaborate in a peer-to-peer manner. To date, discovery schemes trade a long latency for energy efficiency and require a collaborative duty cycle pattern, and thus they are not suitable for interactive mobile applications where a user is unable to configure others’ devices. In this article, we propose Acc , which serves as an on-demand generic discovery accelerating middleware for many deterministic neighbor discovery schemes. Acc leverages the discovery capabilities of neighbor devices, supporting both direct and indirect neighbor discoveries. Further, we present a proactive online rendezvous maintenance mechanism, which is used to reduce delays for the detection of leaving of neighbors. Our evaluations show that Acc -assisted discovery schemes reduce latency by up to 51.8% compared to schemes consuming the same amount of energy. More importantly, to prove the real-world value of Acc , we further present and evaluate a Crowd-Alert application where Acc is employed by taxi drivers to accelerate selection of a direction with fewer competing taxis and more potential passengers, based on a 280GB dataset of more than 14,000 taxis in Shenzhen, the most crowded city in China.

Incorporating the information from direct and indirect neighbors into fitness evaluation enhances the cooperation in the social dilemmas

We propose an improved fitness evaluation method to investigate the evolution of cooperation in the spatial social dilemmas. In our model, a focal player’s fitness is calculated as the linear combination of his own payoff, the average payoffs of direct and indirect neighbors in which two independent selection parameters (α and β) are used to control the proportion of various payoff contribution to the current fitness. Then, the fitness-based strategy update rule is still Fermi-like, and asynchronous update is adopted here. A large plethora of numerical simulations are performed to validate the behaviors of the current model, and the results unambiguously demonstrate that the cooperation level is greatly enhanced by introducing the payoffs from the surrounding players. In particular, the influence of direct neighbors become more evident when compared with indirect neighbors since the correlation between focal players and their direct neighbors is much closer. Current outcomes are significant for us to further illustrate the origin and emergence of cooperation within a wide variety of natural and man-made systems.

Disentangling above- and belowground neighbor effects on the growth, chemistry, and arthropod community on a focal plant.

Neighboring plants can influence arthropods on a focal plant, and this can result in associational resistance or associational susceptibility. These effects can be mediated by above- and belowground interactions between the neighbor and focal plant, but determining the relative contribution of the above- and belowground effects remains an open challenge. We performed a common garden experiment with a design that enabled us to disentangle the above- and belowground effects of five different plant species on the growth and chemistry of the focal plant ragwort (Jacobaea vulgaris), and the arthropod community associated with this plant. Aboveground effects of different neighboring plant species were more important for the growth and quality of J. vulgaris and for the arthropod abundance on this plant than belowground effects of neighbors. This remained true when only indirect neighbor effects (via affecting the biomass or quality of the focal plant) were considered. The aboveground neighbor effects on arthropod abundance on the focal plant were strongly negative. However, the magnitude of the effect depended on the identity of the neighboring species, and herbivore abundance on the focal plant was higher when surrounded by conspecific than when surrounded by heterospecific plants. We also observed interactions between above- and belowground neighbor effects, indicating that these effects may be nonadditive. We conclude that above- and belowground associational effects are not equally strong, and that neighbor effects on plant-arthropod interactions occur predominantly aboveground.

A Random Walk Method Using Trust Factor in Collaborative Filtering

Collaborative filtering is one of the most widely used techniques for recommendation system which has been successfully applied in many applications. However, it suffers from the cold start users who rate only a small fraction of the available items. In addition, these methods can not indicate confidence they are for recommendation. Trust-based rec- ommendation methods assume the additional knowledge of a trust network among users and can alleviate the cold start users, since users only need to be simply connected to the trust network. On the other hand, the sparse user item ratings lead the trust-based method to consider ratings of indirect neighbors that are only weakly trusted, which may decrease its precision. In this paper, we improved the random walk model combining the trust factor-based and the collaborative filter- ing method for recommendation. The trust factor is considered as important a measure of guiding recommendations. The empirical analysis on the Epinions dataset demonstrates that our method outperform other trust-based and collaborative filtering methods.

Why ( n + 1)th‐hop neighbours are more important than n th‐hop ones for localisation in multi‐hop WSNs

For range-free localisation in a wireless sensor network (WSN), the importance of indirect anchor neighbours of an unknown node has been underestimated in the past. In this reported work, for the unknown node, we show that its (n + 1)th-hop anchor neighbours are more useful than its nth-hop ones. By employing a theoretical model to analyse the possible localisation area (PLA) of the unknown node, it is found that the PLA and the hop count are negatively correlated, which indicates that (n + 1)th-hop anchor neighbours can provide more information to more accurately localise the unknown node. Meanwhile, the property of convergence of the theoretical model means that localisation accuracy cannot be unlimitedly improved with increasing hop counts. In the simulations, the presented theory is verified.