Hybrid quantum tensor networks for aeroelastic applications

We investigate the application of hybrid quantum tensor networks to aeroelastic problems, harnessing the power of Quantum Machine Learning (QML). By combining tensor networks with variational quantum circuits, we demonstrate the potential of QML to tackle complex time series classification and regression tasks. Our results showcase the ability of hybrid quantum tensor networks to achieve high accuracy in binary classification. Furthermore, we observe promising performance in regressing discrete variables. While hyperparameter selection remains a challenge, requiring careful optimisation to unlock the full potential of these models, this work contributes significantly to the development of QML for solving intricate problems in aeroelasticity. We present an end-to-end trainable hybrid algorithm. We first encode time series into tensor networks to then utilise trainable tensor networks for dimensionality reduction, and convert the resulting tensor to a quantum circuit in the encoding step. Then, a tensor network inspired trainable variational quantum circuit is applied to solve either a classification or a multivariate or univariate regression task in the aeroelasticity domain.

Analysis of GraphSum's Attention Weights to Improve the Explainability of Multi-Document Summarization

Modern multi-document summarization (MDS) methods are based on transformer architectures. They generate state of the art summaries, but lack explainability. We focus on graph-based transformer models for MDS as they gained recent popularity. We aim to improve the explainability of the graph-based MDS by analyzing their attention weights. In a graph-based MDS such as GraphSum, vertices represent the textual units, while the edges form some similarity graph over the units. We compare GraphSum's performance utilizing different textual units, i. e., sentences versus paragraphs, on two news benchmark datasets, namely WikiSum and MultiNews. Our experiments show that paragraph-level representations provide the best summarization performance. Thus, we subsequently focus oAnalysisn analyzing the paragraph-level attention weights of GraphSum's multi-heads and decoding layers in order to improve the explainability of a transformer-based MDS model. As a reference metric, we calculate the ROUGE scores between the input paragraphs and each sentence in the generated summary, which indicate source origin information via text similarity. We observe a high correlation between the attention weights and this reference metric, especially on the the later decoding layers of the transformer architecture. Finally, we investigate if the generated summaries follow a pattern of positional bias by extracting which paragraph provided the most information for each generated summary. Our results show that there is a high correlation between the position in the summary and the source origin.