A Systematic Survey on Deep Generative Models for Graph Generation

Fast Graph Generation via Spectral Diffusion

Generating graph-structured data is a challenging problem, which requires learning the underlying distribution of graphs. Various models such as graph VAE, graph GANs, and graph diffusion models have been proposed to generate meaningful and reliable graphs, among which the diffusion models have achieved state-of-the-art performance. In this paper, we argue that running full-rank diffusion SDEs on the whole graph adjacency matrix space hinders diffusion models from learning graph topology generation, and hence significantly deteriorates the quality of generated graph data. To address this limitation, we propose an efficient yet effective Graph Spectral Diffusion Model (GSDM), which is driven by low-rank diffusion SDEs on the graph spectrum space. Our spectral diffusion model is further proven to enjoy a substantially stronger theoretical guarantee than standard diffusion models. Extensive experiments across various datasets demonstrate that our proposed GSDM turns out to be the SOTA model, by exhibiting both significantly higher generation quality and much less computational consumption than the baselines.

Computational drug discovery on human immunodeficiency virus with a customized long short-term memory variational autoencoder deep-learning architecture

Despite attempts to control the spread of human immunodeficiency virus (HIV) through the use of anti-HIV medications, the absence of an effective vaccine continues to present a significant obstacle. In addition, the development of drug resistance by HIV underscores the necessity for computational drug discovery methods to identify novel therapies. This investigation specifically focused on employing a long short-term memory (LSTM) variational autoencoder deep-learning architecture for computational drug discovery in relation to HIV. Our data set comprised simplified molecular input line entry system (SMILES)-encoded compounds, which were used to train the LSTM autoencoder. Remarkably, our model achieved a training accuracy of 91%, with a data set containing 1377 compounds. Leveraging the generative model derived from the training phase, we generated potential new drugs for combating HIV and assessed their interaction with the virus using a previously developed artificial intelligence model. Lastly, we verified the drug likeliness of our computationally generated compounds in accordance with Lipinski's rule of five. Overall, our study presents a promising approach to computational drug discovery in the ongoing battle against HIV.

A Semi-Supervised Approach for Improving Generalization in Non-Intrusive Load Monitoring

Non-intrusive load monitoring (NILM) considers different approaches for disaggregating energy consumption in residential, tertiary, and industrial buildings to enable smart grid services. The main feature of NILM is that it can break down the bulk electricity demand, as recorded by conventional smart meters, into the consumption of individual appliances without the need for additional meters or sensors. Furthermore, NILM can identify when an appliance is in use and estimate its real-time consumption based on its unique consumption patterns. However, NILM is based on machine learning methods and its performance is dependent on the quality of the training data for each appliance. Therefore, a common problem with NILM systems is that they may not generalize well to new environments where the appliances are unknown, which hinders their widespread adoption and more significant contributions to emerging smart grid services. The main goal of the presented research is to apply a domain adversarial neural network (DANN) approach to improve the generalization of NILM systems. The proposed semi-supervised algorithm utilizes both labeled and unlabeled data and was tested on data from publicly available REDD and UK-DALE datasets. The results show a 3% improvement in generalization performance on highly uncorrelated data, indicating the potential for real-world applications.