8 May 2023 in IEEE Transactions on Knowledge and Data Engineering
Network alignment aims to discover nodes in different networks belonging to the same identity. In recent years, the network alignment problem has aroused significant attentions in both industry and academia. However, the continuous exploding of network data brings two challenges in solving the network alignment problem, i.e., large network scale and scarce labeled data. To bridge this gap, in this paper we propose a novel approach termed as M ulti-granular I ty N etwork al I gnment based on co N trastive learnin G (MINING). Specifically, in MINING, we first design multi-granularity alignment framework to solve the issue of large network scale. Then, we design intra- and inter-network contrastive learning to solve the issue of scarce labeled data. Moreover, we provide theoretical proofs to demonstrate the effectiveness of MINING. Finally, we conduct extensive experiments on the benchmark datasets of Facebook-Twitter, AMiner-LinkedIn and DBpedia $_{\rm{ZH}}$ -DBpedia $_{\rm{EN}}$ , and results show that MINING can averagely achieve 15.93% higher $\operatorname{Hits@}k$ and 14.82% higher $\operatorname{MRR@}k$ compared with the state-of-the-art methods.
22 May 2023 in ACM Transactions on the Web
Social network alignment, which aims to uncover the correspondence across different social networks, shows fundamental importance in a wide spectrum of applications such as cross-domain recommendation and information propagation. In the literature, the vast majority of the existing studies focus on the social network alignment at user level. In practice, the user-level alignment usually relies on abundant personal information and high-quality supervision, which is expensive and even impossible in the real-world scenario. Alternatively, we propose to study the problem of social group alignment across different social networks, focusing on the interests of social groups rather than personal information. However, social group alignment is non-trivial and faces significant challenges in both (i) feature inconsistency across different social networks and (ii) group discovery within a social network. To bridge this gap, we present a novel GroupAligner , a deep reinforcement learning with domain adaptation for social group alignment. In GroupAligner , to address the first issue, we propose the cycle domain adaptation approach with the Wasserstein distance to transfer the knowledge from the source social network, aligning the feature space of social networks in the distribution level. To address the second issue, we model the group discovery as a sequential decision process with reinforcement learning in which the policy is parameterized by a proposed
p
roximity-enhanced
G
raph
N
eural
N
etwork (pGNN)
and a GNN-based discriminator to score the reward. Finally, we utilize pre-training and teacher forcing to stabilize the learning process of GroupAligner . Extensive experiments on several real-world datasets are conducted to evaluate GroupAligner , and experimental results show that GroupAligner outperforms the alternative methods for social group alignment.
31 October 2022 in IEEE Transactions on Big Data
Network alignment aims to discover nodes in different networks belonging to the same identity. In recent years, the network alignment problem has aroused significant attentions in both industry and academia. With the rapid growth of information, the sizes of networks are usually very large and in most cases we only focus on the alignment of partial networks. However, under this circumstances, the collected network data may be highly biased, and the training and testing data are no longer i.i.d. (identically and independently distributed). Thus, it is difficult for the trained alignment model to have a good performance in the test set. To bridge this gap, in this paper, we propose a novel D omain gener A lization based net W ork alig N ment approach termed as DAWN. Specifically, in DAWN, we first design a novel invariant feature extraction model which leverages adversarial learning to extract domain-invariant features. Then, we design a novel invariant network alignment model which can achieve global optimum and local optimum simultaneously to learn domain-invariant alignment patterns. Finally, we conduct extensive experiments on the benchmark dataset of Facebook-Twitter, and results show that DAWN can averagely achieve 14.01% higher Hits@k and 10.63% higher MRR@k compared with the state-of-the-art methods.
13 June 2024 in IEEE Transactions on Big Data
User profiling has very important applications for many downstream tasks. Most existing methods only focus on modeling user profiles of one social network with plenty of data. However, user profiles are difficult to acquire, especially when the data is scarce. Fortunately, we observed that similar users have similar behavior patterns in different social networks. Motivated by such observations, in this paper, we for the first time propose to study the user profiling problem from the transfer learning perspective. We design two efficient frameworks for User Profile transferring acrOss Networks, i.e., UPON and E-UPON. In UPON, we first design a novel graph convolutional networks based characteristic-aware domain attention model to find user dependencies within and between domains (i.e., social networks). We then design a dual-domain weighted adversarial learning method to address the domain shift problem existing in the transferring procedure. In E-UPON, we optimize UPON in terms of computational complexity and memory. Specifically, we design a mini-cluster gradient descent based graph representation algorithm to shrink the searching space and ensure parallel computation. Then we use an adaptive cluster matching method to adjust the clusters of users. Experimental results on Twitter-Foursquare dataset demonstrate that UPON and E-UPON outperform the state-of-the-art models.
14 March 2026 in Expert Systems with Applications