Recently, novelty detection with reconstruction along projection pathway (RaPP) has made progress toward leveraging hidden activation values. RaPP compares the input and its autoencoder reconstruction in hidden spaces to detect novelty samples. Nevertheless, traditional autoencoders have not yet begun to fully exploit this method. In this paper, we propose a new model, the Extended Autoencoder Model, that adds an adversarial component to the autoencoder to take full advantage of RaPP. The adversarial component matches the latent variables of the reconstructed input to the latent variables of the original input to detect novelty samples with high hidden reconstruction errors. The proposed model can be combined with variants of the autoencoder, such as a variational autoencoder or adversarial autoencoder. The effectiveness of the proposed model was evaluated across various novelty detection datasets. Our results demonstrated that extended autoencoders are capable of outperforming conventional autoencoders in detecting novelties using the RaPP method.

In this paper, we present a new way of detecting dependency patterns in research collaboration environments. We use co-authorship data at the organization level to measure the degree of research collaboration. Thus we adopt a special clustering technique, called ‘cross-associations clustering’, to extract the dependency patterns among research groups. To assist in evaluating the dependency patterns, we suggest a collaboration dependency index to indicate whether a research group is dependent on other groups. In our work, as target research environments, we choose four significant areas: alternative energy, water shortage, food shortage and global warming. Through extensive cluster analysis, we have found that dependency patterns exist in the areas of alternative energy, water shortage and global warming, but not in the food shortage area.

Recently, data-driven decision-making has attracted great interest; this requires high-quality datasets. However, real-world datasets often feature missing values for unknown or intentional reasons, rendering data-driven decision-making inaccurate. If a machine learning model is trained using incomplete datasets with missing values, the inferred results may be biased. In this case, a commonly used technique is the missing value imputation (MVI), which fills missing data with possible values estimated based on observed values. Various data imputation methods using machine learning, statistical inference, and relational database theories have been developed. Among them, conventional machine learning based imputation methods that handle tabular data can deal with only numerical columns or are time-consuming and cumbersome because they create an individualized predictive model for each column. Therefore, we have developed a novel imputational neural network that we term the Denoising Self-Attention Network (DSAN). Our proposed DSAN can deal with tabular datasets containing both numerical and categorical columns; it considers discretized numerical values as categorical values for embedding and self-attention layers. Furthermore, the DSAN learns robust feature expression vectors by combining self-attention and denoising techniques, and can predict multiple, appropriate substituted values simultaneously (via multi-task learning). To verify the validity of the method, we performed data imputation experiments after arbitrarily generating missing values for several real-world tabular datasets. We evaluated both imputational and downstream task performances, and we have seen that the DSAN outperformed the other models, especially in terms of category variable imputation.