Search

Static network embedding has been widely studied to convert sparse structure information into a dense latent space. However, the majority of real networks are continuously evolving, and deriving the whole embedding for every snapshot is computationally intensive. To avoid recomputing the embedding over time, we explore streaming network embedding for two reasons: 1) to efficiently identify the nodes required to update the embeddings under multi-type network changes, and 2) to carefully revise the embeddings to maintain transduction over different parts of the network. Specifically, we propose a new representation learning framework, named Graph Memory Refreshing (GMR), to preserve both global types of structural information efficiently. We prove that GMR maintains the consistency of embeddings (crucial for network analysis) for isomorphic structures better than existing approaches. Experimental results demonstrate that GMR outperforms the baselines with much smaller time.

Studies have shown that each person is more inclined to enjoy a group activity when 1) she is interested in the activity, and 2) many friends with the same interest join it as well. Nevertheless, even with the interest and social tightness information available in online social networks, nowadays many social group activities still need to be coordinated manually. In this paper, therefore, we first formulate a new problem, named Participant Selection for Group Activity (PSGA), to decide the group size and select proper participants so that the sum of personal interests and social tightness of the participants in the group is maximized, while the activity cost is also carefully examined. To solve the problem, we design a new randomized algorithm, named Budget-Aware Randomized Group Selection (BARGS), to optimally allocate the computation budgets for effective selection of the group size and participants, and we prove that BARGS can acquire the solution with a guaranteed performance bound. The proposed algorithm was implemented in Facebook, and experimental results demonstrate that social groups generated by the proposed algorithm significantly outperform the baseline solutions.

The social presence theory in social psychology suggests that computer-mediated online interactions are inferior to face-to-face, in-person interactions. In this paper, we consider the scenarios of organizing in person friend-making social activities via online social networks (OSNs) and formulate a new research problem, namely, Hop-bounded Maximum Group Friending (HMGF), by modeling both existing friendships and the likelihood of new friend making. To find a set of attendees for socialization activities, HMGF is unique and challenging due to the interplay of the group size, the constraint on existing friendships and the objective function on the likelihood of friend making. We prove that HMGF is NP-Hard, and no approximation algorithm exists unless \(P=NP\). We then propose an error-bounded approximation algorithm to efficiently obtain the solutions very close to the optimal solutions. We conduct a user study to validate our problem formulation and perform extensive experiments on real datasets to demonstrate the efficiency and effectiveness of our proposed algorithm.