With the advancement of deep learning, DNNs have been widely deployed across diverse domains. Model-as-a-Service (MaaS) platforms allow enterprises to commercialize well-trained models, which are built through extensive data collection and substantial computational investment. Consequently, protecting these models from unauthorized use and intellectual property (IP) theft has become critical. While watermarking has emerged as a prominent IP protection technique, most existing approaches target centralized settings, leaving federated learning (FL) scenarios largely underexplored. To bridge this gap, we propose Federated Watermarking with Distributed Verification (FWDV), a novel framework tailored for FL. FWDV enables each client to independently verify watermark ownership and jointly defend the model against erasure attempts. To our knowledge, this is the first work to achieve both distributed verification and robustness against a broad spectrum of attacks. Extensive experiments demonstrate that FWDV embeds watermarks with minimal impact on model utility and resists removal through fine-tuning, pruning, and distillation.

Link prediction is one of the most fundamental tasks in graph mining, which motivates the recent studies of leveraging contrastive learning to enhance the performance. However, we observe two major weaknesses of these studies: i) the lack of theoretical analysis for contrastive learning on link prediction, and ii) inadequate consideration of node degrees in contrastive learning. To address the above weaknesses, we provide the first formal theoretical analysis for contrastive learning on link prediction, where our analysis results can generalize to the autoencoder-based link prediction models with contrastive learning. Motivated by our analysis results, we propose a new graph augmentation approach, Edge Balancing Augmentation (EBA), which adjusts the node degrees in the graph as the augmentation. We then propose a new approach, named Contrastive Link Prediction with Edge Balancing Augmentation (CoEBA), that integrates the proposed EBA and the proposed new contrastive losses to improve the model performance. We conduct experiments on 8 benchmark datasets. The results demonstrate that our proposed CoEBA significantly outperforms the other state-of-the-art link prediction models.

The$k$-plex is a popular definition of communities in networks, offering more flexibility than cliques by allowing each node to miss up to$k$connections. However, finding$k$-plexes in large graphs is a theoretically challenging task due to the large number of possible$k$-plexes. In this article, we propose a novel approach for detecting$k$-plexes under various sizes and time constraints using an automated strategy to learn bounds, called theconstraint learning and bounding (CLB)method. Specifically, our proposedCLBapproach, leverages the concept of constraint learning to develop a mixed integer linear programming (MILP) instance as a model to learn a bounding strategy in the branch-and-bound process. The variables in the MILP instances correspond to the natural properties of the$k$-plex problem. Unlike previous works, we focus on learning the bounding strategy rather than learning the branching strategy. Thus, the strategy learned by our proposed approach avoids visiting infeasible solutions, which accelerates the branch-and-bound algorithm and reduces the computational load. To evaluate our approach, we conduct experiments on various real graphs to validate the superiority and the generality of our proposed approach. In summary, our approach offers an effective and efficient solution for detecting$k$-plexes under various conditions.

Research suggests that social relationships have substantial impacts on individuals’ health outcomes. Network intervention, through careful planning, can assist a network of users to build healthy relationships. However, most previous work is not designed to assist such planning by carefully examining and improving multiple network characteristics. In this paper, we propose and evaluate algorithms that facilitate network intervention planning through simultaneous optimization of network degree, closeness, betweenness, and local clustering coefficient, under scenarios involving Network Intervention with Limited Degradation - for Single target (NILD-S) and Network Intervention with Limited Degradation - for Multiple targets (NILD-M). We prove that NILD-S and NILD-M are NP-hard and cannot be approximated within any ratio in polynomial time unless P=NP. We propose the Candidate Re-selection with Preserved Dependency (CRPD) algorithm for NILD-S, and the Objective-aware Intervention edge Selection and Adjustment (OISA) algorithm for NILD-M. Various pruning strategies are designed to boost the efficiency of the proposed algorithms. Extensive experiments on various real social networks collected from public schools and Web and an empirical study are conducted to show that CRPD and OISA outperform the baselines in both efficiency and effectiveness.

With the advance of the photovoltaic panel technology, the infrastructure equipment of cellular networks with solar energy sources has attracted extensive interests. It is expected that base stations (BSs) and relay stations (RSs) with renewable energy will play important roles in reducing the power consumption from electrical grids in future green cellular networks. Inspired by this technology trend, this paper considers a heterogeneous green cellular network, in which a part of RSs is powered by solar energy sources to represent the incremental deployment for the infrastructure with renewable energy in the near future. We formulate a new relay selection and power allocation problem with Mixed Integer Linear Programming to select solar-powered RSs and grid-powered RSs, such that the total grid power consumption is effectively minimized in decode-and-forward cooperative communication networks. We design an algorithm to derive the optimal solution, and also devise an efficient distributed algorithm to reduce the computational cost. The simulation results demonstrate that the algorithms can effectively reduce the total grid power consumption with different channel conditions, different deployments of RSs in a network, and different available power levels in solar-powered RSs. In addition, the problem model and the proposed algorithms can be extended to support hybrid energy sources.

Owing to the rising popularity of online social networking services (OSNs), studies on social influence and its diffusion have received significant attention from the research community. Prior research has mostly studied the impact of single-hop influence diffusion and multi-hop influence broadcast in online social networks. Very little research explores the idea of guiding (routing) multi-hop social influence towards a specific target. In this paper, we motivate the needs of timely routing social influence to formulate a new optimization problem, namely, Routing And Scheduling of Target-Oriented Social Influence Diffusion (RAS-TOSID). Accordingly, we propose the Efficient Routing And Scheduling with Social and Temporal decOmposition (ERASSTO) algorithm, which finds the optimal solution to RAS-TOSID in polynomial time. We carry out a user study by implementing ERASSTO in Facebook and conduct a comprehensive evaluation on ERASSTO and alternative approaches by simulation. The result shows that ERASSTO significantly outperforms other algorithms regarding solution quality and computational efficiency.

Research issues and data mining techniques for product recommendation and viral marketing have been widely studied. Existing works on seed selection in social networks do not take into account the effect of product recommendations in e-commerce stores. In this paper, we investigate the seed selection problem for viral marketing that considers both effects of social influence and item inference (for product recommendation). We develop a new model, Social Item Graph (SIG), that captures both effects in the form of hyperedges. Accordingly, we formulate a seed selection problem, called Social Item Maximization Problem (SIMP), and prove the hardness of SIMP. We design an efficient algorithm with performance guarantee, called Hyperedge-Aware Greedy (HAG), for SIMP and develop a new index structure, called SIG-index, to accelerate the computation of diffusion process in HAG. Moreover, to construct realistic SIG models for SIMP, we develop a statistical inference based framework to learn the weights of hyperedges from data. Finally, we perform a comprehensive evaluation on our proposals with various baselines. Experimental result validates our ideas and demonstrates the effectiveness and efficiency of the proposed model and algorithms over baselines.

Business location planning, critical to success of many businesses, can be addressed by reverse nearest neighbors (RNN) query using geographical proximity to the customers as the main metric to find a store location which is the closest to many customers. Nevertheless, we argue that other marketing factors such as social influence could be considered in the process of business location planning. In this paper, we propose a framework for business location planning that takes into account both factors of geographical proximity and social influence. An essential task in this framework is to compute the “influence spread” of RNNs for candidate locations. However, excessive computational overhead and long latency hinder its feasibility for our framework. Thus, we trade storage overhead for the processing speed by precomputing and storing the social influences between pairs of customers and design a suite of algorithms based on Targeted Region-oriented strategy. Various ordering and pruning techniques have been incorporated in these algorithms to enhance the processing efficiency of our framework. Experiments also show that the proposed algorithms efficiently support the task of location planning under various parameter settings.

Software-Defined Networking (SDN) enables flexible network resource allocations for traffic engineering, but at the same time the scalability problem becomes more serious since traffic is more difficult to be aggregated. Those crucial issues in SDN have been studied for unicast but have not been explored for multicast traffic, and addressing those issues for multicast is more challenging since the identities and the number of members in a multicast group can be arbitrary. In this paper, therefore, we propose a new multicast tree for SDN, named Branch-aware Steiner Tree (BST). The BST problem is difficult since it needs to jointly minimize the numbers of the edges and the branch nodes in a tree, and we prove that it is NP-Hard and inapproximable within k, which denotes the number of group members. We further design an approximation algorithm, called Branch Aware Edge Reduction Algorithm (BAERA), to solve the problem. Simulation results demonstrate that the trees obtained by BAERA are more bandwidth-efficient and scalable than the shortest-path trees and traditional Steiner trees. Most importantly, BAERA is computation-efficient to be deployed in SDN since it can generate a tree on massive networks in small time.

To many location-based service applications that prefer diverse results, finding locations that are spatially diverse and close in proximity to a query point (e.g., the current location of a user) can be more useful than finding the k nearest neighbors/locations. In this paper, we investigate the problem of searching for the k Diverse-Near Neighbors (kDNNs)} in spatial space that is based upon the spatial diversity and proximity of candidate locations to the query point. While employing a conventional distance measure for proximity, we develop a new and intuitive diversity metric based upon the variance of the angles among the candidate locations with respect to the query point. Accordingly, we create a dynamic programming algorithm that finds the optimal kDNNs. Unfortunately, the dynamic programming algorithm, with a time complexity of O(kn3), incurs excessive computational cost. Therefore, we further propose two heuristic algorithms, namely, Distance-based Browsing (DistBrow) and Diversity-based Browsing (DivBrow) that provide high effectiveness while being efficient by exploring the search space prioritized upon the proximity to the query point and spatial diversity, respectively. Using real and synthetic datasets, we conduct a comprehensive performance evaluation. The results show that DistBrow and DivBrow have superior effectiveness compared to state-of-the-art algorithms while maintaining high efficiency.

Friending recommendation has successfully contributed to the explosive growth of online social networks. Most friending recommendation services today aim to support passive friending, where a user passively selects friending targets from the recommended candidates. In this paper, we advocate a recommendation support for active friending, where a user actively specifies a friending target. To the best of our knowledge, a recommendation designed to provide guidance for a user to systematically approach his friending target has not been explored for existing online social networking services. To maximize the probability that the friending target would accept an invitation from the user, we formulate a new optimization problem, namely, Acceptance Probability Maximization (APM), and develop a polynomial time algorithm, called Selective Invitation with Tree and In-Node Aggregation (SITINA), to find the optimal solution. We implement an active friending service with SITINA on Facebook to validate our idea. Our user study and experimental results reveal that SITINA outperforms manual selection and the baseline approach in solution quality efficiently.

Prior research on viral marketing mostly focuses on promoting one single product item. In this work, we explore the idea of bundling multiple items for viral marketing and formulate a new research problem, called Bundle Configuration for SpreAd Maximization (BCSAM). Efficiently obtaining an optimal product bundle under the setting of BCSAM is very challenging. Aiming to strike a balance between the quality of solution and the computational overhead, we systematically explore various heuristics to develop a suite of algorithms, including κ-Bundle Configuration and Aggregated Bundle Configuration. Moreover, we integrate all the proposed ideas into one efficient algorithm, called Aggregated Bundle Configuration (ABC). Finally, we conduct an extensive performance evaluation on our proposals. Experimental results show that ABC significantly outperforms its counterpart and two baseline approaches in terms of both computational overhead and bundle quality.