Designing molecules with specific attributes is vital in drug discovery and materials science.Ring structures are key to a molecule's stability, reactivity, and biological interactions, ensuring that designed compounds are both feasible and synthetically viable, thereby increasing their potential for lab production and therapeutic use.Generative diffusion models have become essential tools for in silico molecule generation.However, integrating structural constraints, especially those involving ring structures, remains challenging.This study introduces a method for applying hard ring-related constraints in molecule generation, enhancing synthetic validity and utility, with evaluations on the QM9 dataset.

In recent years, there has been a growing interest in using generative models for de novo drug design. State-of-the-Art methods typically focus on either 2D structures or 3D structures, also known as conformers. Designing 3D structures is more challenging because it involves predicting spatial coordinates, necessitating the use of SE(3) equivariant architectures to ensure consistency under coordinate transformations like rotations and translations. This study presents D4, a novel Distance and Discrete Denoising Diffusion model that utilizes the distance matrix of molecular atoms to predict a molecule’s 3D coordinates, which are naturally unaffected by such transformations. This method effectively sidesteps the difficulties encountered with traditional coordinate-based training done by State-of-the-Art methods and allows explicit conditioning of bond types on distances. The experiments performed on three well-established datasets — QM9, GDB13, and ZINC250K — of varying challenges show that this approach significantly surpasses the performance of MiDi, a State-of-the-Art approach for generating 3D molecular structures. Additionally, an ablation study confirms the significance of adopting a novel regularization loss, which addresses errors in distance predictions and bounds the triangle inequality, validating the use of distance matrices in molecular generative models. • Generation of 3D molecules through distance and discrete denoising diffusion • SE(3) equivariance is built into the model by the use of distances • A loss on eigenvalues leads to better generation of Euclidean Distance Matrices in 3D • D4 surpasses State-of-the-Art model in the generation of realistic dis- tances in QM9, ZINC, and GDB13 • KDEs offer additional qualitative insights, showing improved distribu- tion learning

Abstract Lead-lag relationships and effects among financial assets are fundamental for understanding market dynamics and predicting price movements. However, accurately detecting these evolving temporal dependencies remains a complex challenge. Traditional approaches predominantly rely on statistical methods based on price evidence, while machine learning and deep learning techniques remain largely unexplored in this context. The lead-lag relationships and effects can be naturally represented using a dynamic graph structure, although this direction is still uninvestigated in the literature. Indeed, existing studies rarely leverage graph-based representations, and when they do, they typically consider static rather than dynamic structures, limiting their ability to capture temporal evolution. To overcome these limitations, this study proposes a novel framework that: (i) formulates lead-lag relationships and effects detection as a temporal link prediction task on dynamic graphs; (ii) introduces a novel real-world benchmark task for the evaluation and comparison of Temporal Graph Neural Networks (TGNNs); (iii) adapts, extends, and defines nine deep learning models ranging from simple LSTMs to State-of-the-Art TGNNs; (iv) explicitly evaluates two scenarios: lead-lag relationships that are both positive and negative, as well as those that are only positive; (v) performs an ablation study to assess the impact of the key components of the considered approaches. The experiments were conducted on a custom-gathered dataset of financial assets enriched with temporal, structural, and sentiment features. The findings demonstrate that temporal graph learning effectively models complex lead-lag relationships, opening new avenues for data-driven financial market analysis.

The rapidly evolving field of machine learning for graphstructured data gathered significant attention due to its ability to preserve critical information inherent in complex data structures.As a result, significant efforts have been dedicated to designing advanced architectures and foundational models optimized for graph-based operations.Research in this area explores methodologies for graph representation learning and graph generation, incorporating probabilistic models such as variational autoencoders and normalizing flows.Despite increasing interest from researchers as well as their efforts in solving graph-related problems, several issues and areas remain to be addressed to improve model generalization and reliability.This tutorial reviews foundational concepts and challenges in graph representation, structure learning, and graph generation, while also summarizing the contributions accepted for publication in the special session on this topic at the 33th European

Recent years have witnessed an increase in interest in leveraging generative models for de novo molecular design in drug discovery.Many State-of-the-Art (SotA) models incorporate the 3D structural information of the molecule, particularly atomic spatial coordinates.However, such approaches face challenges integrating SE(3) equivariance when trained on coordinates.This work explores the use of the distance matrix for molecular structures, natively SE(3) invariant, avoiding whatever the issue.Experimental evaluation shows that our proposed approach significantly improves upon MiDi, a SotA 3D molecule generator.

Shell and tube heat exchangers are essential for many industries, as they allow to control of temperatures in industrial processes. Designing shell and tube heat exchangers is a complex task as they are governed by differential equations and influenced by numerous variables. Calculating the performance of a heat exchanger, based on variables such as the shape, number, and length of tubes, requires solving time-consuming differential equations or using simplified estimates requiring specialist expertise. This paper introduces a novel approach using deep neural networks to predict the required shell and tube heat exchanger variables based on the customer’s required capacities and pressures. This is achieved through two sequential phases: a pre-training on estimated values and, subsequently, a fine-tuning on a smaller dataset comprising measurements collected from real-world products. This method eliminates the need for iterative processes and complex equations, offering faster and accurate predictions. In addition, the paper highlights the phenomenon of "double descent" in neural networks, as it was crucial for optimizing performance. This approach enables companies to customize reliable exchangers efficiently, reducing time and specialist efforts.

Abstract Identifying molecules that exhibit some pre-specified properties is a difficult problem to solve. In the last few years, deep generative models have been used for molecule generation. Deep Graph Variational Autoencoders are among the most powerful machine learning tools with which it is possible to address this problem. However, existing methods struggle to capture the true data distribution and tend to be computationally expensive. In this work, we propose RGCVAE, an efficient and effective Graph Variational Autoencoder based on: (i) an encoding network exploiting a new powerful Relational Graph Isomorphism Network; (ii) a novel probabilistic decoding component. Compared to several State-of-the-Art VAE methods on two widely adopted datasets, RGCVAE shows State-of-the-Art molecule generation performance while being significantly faster to train. The Python code implementing RGCVAE is openly accessible for download at: https://github.com/drigoni/RGCVAE .

Named Entity Recognition is a crucial task in Natural Language Processing (NLP) which aims to identify the entities in text. Given an adequate amount of annotated data, Large Language Models (LLMs) have been shown to be effective in this task when fine-tuned. However, the performance of LLMs is severely affected when annotated datasets are limited. To alleviate this problem, adding synthetic data via Data Augmentation (DA) techniques is a viable approach. Even so, DA for token-level tasks suffers from two main limitations: (i) token-label misalignment problem; and (ii) quality of generated synthetic data. In this paper, we propose a novel prompt-based DA approach using contrastive learning. The proposed method can generate high-quality synthetic data while preserving the token-label correspondences. Experimental results demonstrate that the proposed approach, when compared against multiple baselines on well-known Named Entity Recognition (NER) datasets, achieves State-of-the-Art performance.

Abstract Object detectors are used for searching all objects belonging to a pre-defined set of categories contained in a given picture. However, users are often not interested in finding all objects, but only those that pertain to a small set of categories or concepts. Nowadays, the standard approach to solve this task involves initially employing an object detector to identify all objects within the image, followed by refining the outcomes to retain only the ones of interest. Nevertheless, the object detector does not take advantage of the user’s prior intent that, when used, can potentially improve the detection performance of the model. This work presents a method to condition an existing object detector with the user’s intent, encoded as one or more concepts from the WordNet graph, to find just those objects of interest. The proposed approach takes advantage of existing datasets for object detection without the need for new annotations, and it allows to adapt the already existing object detector models with minor changes. The evaluation, performed on the COCO and the Visual Genome datasets considering several object detector architectures, shows that conditioning the search on concepts is actually beneficial. The code and the pre-trained model weights are released at: https://github.com/drigoni/Concept-Conditioned-Object-Detector .