Most real-world networks suffer from incompleteness or incorrectness, which is an inherent attribute to real-world datasets. As a consequence, those downstream machine learning tasks in complex network like community detection methods may yield less satisfactory results, i.e., a proper preprocessing measure is required here. To address this issue, in this paper, we design a new community attribute based link prediction strategy HAP and propose a two-step community enhancement algorithm with automatic evolution process based on HAP. This paper aims at providing a community enhancement measure through adding links to clarify ambiguous community structures. The HAP method takes the neighbourhood uncertainty and Shannon entropy to identify boundary nodes, and establishes links by considering the nodes' community attributes and community size at the same time. The experimental results on twelve real-world datasets with ground truth community indicate that the proposed link prediction method outperforms other baseline methods and the enhancement of community follows the expected evolution process.

Determining causal effects of temporal multi-intervention assists decision-making. Restricted by time-varying bias, selection bias, and interactions of multiple interventions, the disentanglement and estimation of multiple treatment effects from individual temporal data is still rare. To tackle these challenges, we propose a comprehensive framework of temporal counterfactual forecasting from an individual multiple treatment perspective (TCFimt). TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy. Through implementing experiments on two real-world datasets from distinct fields, the proposed method shows satisfactory performance in predicting future outcomes with specific treatments and in choosing optimal treatment type and timing than state-of-the-art methods.

In these areas, data can be usually represented as graphs with labels. For example, in bioinformatics, a protein molecule can be represented as a graph whose nodes corresponds to atoms, and edges signify there exits chemical bonds or not between atoms. The graphs are allocated with different labels based on having specific function or not. To make classification in this task, we usually make a common assumption that protein molecules with similar structure have similar functional properties. More recently, there has been a surge of approaches that seek to learn representations or embeddings that encode features about the graphs and then make classification. The idea behind these learning approaches focuses on graph structure representation and learning a mapping that embeds nodes or entire (sub)graphs, into a low-dimensional vector. Most of these methods can be classified into two categories: (1) neural networks manners [4] that learn the large-scale structures of target graph, (2) kernel methods [5] that learn small-size structures of target graph. Different structures of graph imply dissimilar features. Corresponding author Email address: weiw@buaa.edu.cn