Search

The session-based recommendation system aims to predict the user's next click based on their previous session sequence. The current studies generally learn user preferences according to the transitions of items in the user's session sequence. However, other effective information in the session sequence, such as user profiles, is largely ignored which may lead to the model unable to learn the user's specific preferences. In this paper, we propose SR-HetGNN, a novel session recommendation method that uses a heterogeneous graph neural network (HetGNN) to learn session embeddings and capture the specific preferences of anonymous users. Specifically, SR-HetGNN first constructs heterogeneous graphs containing various types of nodes according to the session sequence, which can capture the dependencies among items, users, and sessions. Second, HetGNN captures the complex transitions between items and learns the item embeddings containing user information. Finally, local and global session embeddings are combined with the attentional network to obtain the final session embedding, considering the influence of users' long and short-term preferences. SR-HetGNN is shown to be superior to the existing state-of-the-art session-based recommendation methods through extensive experiments over two real large datasets Diginetica and Tmall. The code and datasets can be found in our GitHub repository https://github.com/LeeHY1996/SR-HetGNN. [ABSTRACT FROM AUTHOR]

Graph Neural networks (GNNs) which are powerful and widely applied models are based on the assumption that graph topologies play key roles in the graph representation learning.However, the existing GNN methods are based on the Euclidean space embedding, which is difficult to represent a variety of graph geometric properties well. Recently, Riemannian geometries have been introduced into GNNs, such as Hyperbolic Graph Neural Networks proposed for the hierarchy-preserving graph representation learning. In Riemannian geometry, the different graph topological structures can be reflected by corresponding curved embedding spaces, such as a hyperbolic space can be understood as a continuous tree-like structure and a spherical space can be understood as a continuous clique. However, most existing non-Euclidean GNNs are based on heuristic, manual statistical, or estimation methods, which is difficult to automatically select the appropriate embedding space for graphs with different topological properties. To deal with this problem, we propose the Adaptive Curvature Exploration Geometric Graph Neural Network to automatically learn high-quality graph representations and explore the embedding space with optimal curvature at the same time. We optimize the multi-objective optimization problem of the graph representation learning and curvature exploration with the multi-agent reinforcement learning and using the Nash Q-learning algorithm to collaboratively train the two agents to reach Nash equilibrium. We construct extensive experiments including synthetic and real-world graph datasets, and the results demonstrate significant and consistent performance improvement and generalization of our method. [ABSTRACT FROM AUTHOR]

Network embedding aims to learn a low-dimensional representation vector for each node while preserving the inherent structural properties of the network, which could benefit various downstream mining tasks such as link prediction and node classification. Most existing works can be considered as generative models that approximate the underlying node connectivity distribution in the network, or as discriminate models that predict edge existence under a specific discriminative task. Although several recent works try to unify the two types of models with adversarial learning to improve the performance, they only consider the local pairwise connectivity between nodes. Higher-order structural information such as communities, which essentially reflects the global topology structure of the network, is largely ignored. To this end, we propose a novel framework called CANE to simultaneously learn the node representations and identify the network communities. The two tasks are integrated and mutually reinforce each other under a novel adversarial learning framework. Specifically, with the detected communities, CANE jointly minimizes the pairwise connectivity loss and the community assignment error to improve node representation learning. In turn, the learned node representations provide high-quality features to facilitate community detection. Experimental results on multiple real datasets demonstrate that CANE achieves substantial performance gains over state-of-the-art baselines in various applications including link prediction, node classification, recommendation, network visualization, and community detection. [ABSTRACT FROM AUTHOR]

Collaborative filtering (CF) is a widely adopted technique in recommender systems. Traditional CF models mainly focus on predicting the user preference to items in a single domain, such as the movie domain or the music domain. A major challenge for such models is the data sparsity, and especially, CF cannot make accurate predictions for the cold-start users who have no ratings at all. Although cross-domain collaborative filtering (CDCF) is proposed for effectively transferring knowledge across different domains, it is still difficult for existing CDCF models to tackle the cold-start users in the target domain due to the extreme data sparsity. In this paper, we propose the cross-domain latent feature mapping (CDLFM) model for the cold-start users in the target domain. Firstly, in order to alleviate the data sparsity in single domain and provide essential knowledge for next step, we take users' rating behaviors into consideration and propose the matrix factorization by incorporating user similarities. Next, to transfer knowledge across domains, we propose the neighborhood-based cross-domain latent feature mapping method. For each cold-start user, we learn his/her feature mapping function based on his/her neighbor linked users. By adopting gradient boosting trees and multilayer perceptron to model the cross-domain feature mapping function, two CDLFM models named CDLFM-GBT and CDLFM-MLP are proposed. Experimental results on two real datasets demonstrate the superiority of our proposed model against other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Currently, many intelligence systems contain the texts from multi-sources, e.g., bulletin board system posts, tweets and news. These texts can be "comparative" since they may be semantically correlated and thus provide us with different perspectives toward the same topics or events. To better organize the multi-sourced texts and obtain more comprehensive knowledge, we propose to study the novel problem of Mutual Clustering on Comparative Texts (MCCT), which aims to cluster the comparative texts simultaneously and collaboratively. The MCCT problem is difficult to address because 1) comparative texts usually present different data formats and structures and thus, they are hard to organize and 2) there lacks an effective method to connect the semantically correlated comparative texts to facilitate clustering them in an unified way. To this aim, in this paper, we propose a Heterogeneous Information Network-based Text clustering framework HINT. HINT first models multi-sourced texts (e.g. news and tweets) as heterogeneous information networks by introducing the shared "anchor texts" to connect the comparative texts. Next, two similarity matrices based on HINT as well as a transition matrix for cross-text-source knowledge transfer are constructed. Comparative texts clustering are then conducted by utilizing the constructed matrices. Finally, a mutual clustering algorithm is also proposed to further unify the separate clustering results of the comparative texts by introducing a clustering consistency constraint. We conduct extensive experimental on three tweets-news datasets, and the results demonstrate the effectiveness and robustness of the proposed method in addressing the MCCT problem. [ABSTRACT FROM AUTHOR]

Traditional stock market prediction methods commonly only utilize the historical trading data, ignoring the fact that stock market fluctuations can be impacted by various other information sources such as stock-related events. Although some recent works propose event-driven prediction approaches by considering the event data, how to leverage the joint impacts of multiple data sources still remains an open research problem. In this work, we study how to explore multiple data sources to improve the performance of the stock prediction. We introduce an extended coupled hidden Markov model incorporating the news events with the historical trading data. To address the data sparsity issue of news events for each single stock, we further study the fluctuation correlations between the stocks and incorporate the correlations into the model to facilitate the prediction task. Evaluations on China A-share market data in 2016 show the superior performance of our model against previous methods. [ABSTRACT FROM AUTHOR]

Studying the bursty nature of cascades in social media is practically important in many real applications such as product sales prediction, disaster relief, and stock market prediction. Although both the cascade size prediction and the burst patterns of the cascades have been extensively studied, how to predict when a burst will come remains an open problem. It is challenging for traditional time-series-based models such as regression models to address this task directly. Firstly, times-series-based prediction models focus on predicting the future values based on previously observed ones. It is hard to apply them to predict the time of a bursts with the 'quick rise-and-fall' pattern. Secondly, besides the cascade popularity, a lot of other side information like user profile and social relation are available in social media. Although the potential utility of such information can be high, it is also hard for time-series-based models to capture and integrate these rich information with diverse formats seamlessly. This paper proposes a classification-based approach for burst time prediction by exploiting rich knowledge in information diffusion. Particularly, we first propose a time-window-based transformation to predict in which time window the burst will appear. By dividing the time spans of all the cascades into the same number of time windows K, the cascades with diverse time spans can thus be handled uniformly. To exploit the rich and heterogenous information in social media, we next propose a scale-independent feature extraction framework to model the heterogenous knowledge in a scale-independent manner. Systematical evaluations are conducted on the Sina Weibo reposting dataset and MemeTracker dataset. Besides the superior performance of the proposed approach, we also observe that: (1) surprisingly, social/structure knowledge is more indicative of the bursts than the cascade popularity information, especially for the bursts occurring in a farther future. (2) Larger cascades are harder to predict as the spreading process of the cascades with higher popularity is usually more diverse and fluctuant. (3) The proposed approach is robust in the sense that the result is not much sensitive to the popularity of the training cascades. [ABSTRACT FROM AUTHOR]