Deep learning methods on graph data have achieved remarkable efficacy across a variety of real-world applications, such as social network analysis and transaction risk detection. Nevertheless, recent studies have illuminated a concerning fact: even the most expressive Graph Neural Networks (GNNs) are vulnerable to graph adversarial attacks. While several methods have been proposed to enhance the robustness of GNN models against adversarial attacks, few have focused on a simple yet realistic approach: valuing the adversarial risks and focused safeguards at the node level. This empowers defenders to allocate heightened security level to vulnerable nodes, while lower to robust nodes. With this new perspective, we propose a novel graph defense strategy RisKeeper, such that the adversarial risk can be directly kept in the input graph. We start at valuing the adversarial risk, by introducing a cost-aware projected gradient descent attack that takes into account both cost avoidance and compliance with costs budgets. Subsequently, we present a learnable approach to ascertain the ideal security level for each individual node by solving a bi-level optimization problem. Through extensive experiments on four real-world datasets, we demonstrate that our method achieves superior performance surpassing state-of-the-art methods. Our in-depth case studies provide further insights into vulnerable and robust structural patterns, serving as inspiration for practitioners to exercise heightened vigilance.

The public sharing of user information opens the door for adversaries to infer private data, leading to privacy breaches and facilitating malicious activities. While numerous studies have concentrated on privacy leakage via public user attributes, the threats associated with the exposure of user relationships, particularly through network structure, are often neglected. This study aims to fill this critical gap by advancing the understanding and protection against privacy risks emanating from network structure, moving beyond direct connections with neighbors to include the broader implications of indirect network structural patterns. To achieve this, we first investigate the problem of Graph Privacy Leakage via Structure (GPS), and introduce a novel measure, the Generalized Homophily Ratio, to quantify the various mechanisms contributing to privacy breach risks in GPS. Based on this insight, we develop a novel graph private attribute inference attack, which acts as a pivotal tool for evaluating the potential for privacy leakage through network structures under worst-case scenarios. To protect users' private data from such vulnerabilities, we propose a graph data publishing method incorporating a learnable graph sampling technique, effectively transforming the original graph into a privacy-preserving version. Extensive experiments demonstrate that our attack model poses a significant threat to user privacy, and our graph data publishing method successfully achieves the optimal privacy-utility trade-off compared to baselines.

The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to financial inclusion. It brings non-trivial social benefits of diminishing financial inequality. However, the technical challenges in individual financial risk evaluation exacerbated by the unforeseen user characteristic distribution and limited credit history of new users, as well as the inexperience of newly-entered companies in handling complex data and obtaining accurate labels, impede further promotion of financial inclusion. To tackle these challenges, this paper develops a novel transfer learning algorithm (i.e., TransBoost) that combines the merits of tree-based models and kernel methods. The TransBoost is designed with a parallel tree structure and efficient weights updating mechanism with theoretical guarantee, which enables it to excel in tackling real-world data with high dimensional features and sparsity in O(n) time complexity. We conduct extensive experiments on two public datasets and a unique largescale dataset from Tencent Mobile Payment. The results show that the TransBoost outperforms other state-of-the- art benchmark transfer learning algorithms in terms of prediction accuracy with superior efficiency, demonstrate stronger robustness to data sparsity, and provide meaningful model interpretation. Besides, given a financial risk level, the TransBoost enables financial service providers to serve the largest number of users including those who would otherwise be excluded by other algorithms. That is, the TransBoost improves financial inclusion.

Voting mechanisms are widely adopted for evaluating the quality and credibility of user-generated content, such as online product reviews. For the reviews that do not receive sufficient votes, techniques and models are developed to automatically assess their helpfulness levels. Existing methods serving this purpose are mostly centered on feature analysis, ignoring the information conveyed in the frequencies and patterns of user votes. Consequently, the accuracy of helpfulness measurement is limited. Inspired by related findings from prediction theories and consumer behavior research, we propose a novel approach characterized by the technique of iterative Bayesian distribution estimation, aiming to more accurately measure the helpfulness levels of reviews used for training prediction models. Using synthetic data and a real-world data set involving 1.67 million reviews and 5.18 million votes from Amazon, a simulation experiment and a two-stage data experiment show that the proposed approach outperforms existing methods on accuracy measures. Moreover, an out-of-sample user study is conducted on Amazon Mechanical Turk. The results further illustrate the predictive power of the new approach. Practically, the research contributes to e-commerce by providing an enhanced method for exploiting the value of user-generated content. Academically, we contribute to the design science literature with a novel approach that may be adapted to a wide range of research topics, such as recommender systems and social media analytics.

Concerning the information overload of online reviews, this paper models a new review selection problem called the Informative Review Subset Selection problem (namely, IRSS) and demonstrates that it is NP-hard to solve and approximate. Furthermore, a novel heuristic method (namely, Combined Search-ComS) is proposed for seeking the solution to the problem and selecting a subset of reviews, which is consistent with the original review corpus in light of mutual information entropy. The proposed method is then comprehensively examined via extensive data experiments and a user study on Amazon data. Experimental results reveal the overall superiority of the proposed method in comparison with other extant methods of concern, showing that it is an effective way to select an informative subset of online reviews. The proposed method is deemed desirable and useful for online consumers and service providers.