Explore the vast range of titles available.

This article examines the readiness of EU member states to establish innovation parks by evaluating gross domestic expenditure on research and development (GERD) and the proportion of R&D personnel within the labor force. Utilizing k-means clustering, the research categorizes EU countries into three clusters based on GERD and R&D personnel metrics, allowing for a nuanced assessment of innovation potential. The analysis reveals significant disparities among EU member states, with Austria, Belgium, Denmark, Finland, Germany, and Sweden exhibiting the highest readiness for innovation parks, while others, such as Bulgaria and Romania, face substantial challenges due to limited R&D investment and workforce. This study focuses solely on GERD and R&D personnel, excluding other factors such as government policy or sectoral distinctions. Future research could integrate these elements for a more comprehensive analysis. Insights from this research can guide policymakers in tailoring interventions to enhance R&D funding and workforce development, particularly in underprepared regions. This study contributes to understanding EU innovation readiness by providing a comparative analysis based on financial and human capital, offering a novel clustering approach to assess innovation park potential across diverse EU contexts.

У сучасних умовах продовження збройної агресії росії на території України забезпечення миру та справедливості є одним із першочергових завдань на порядку денного існування держави. Водночас, поряд із соціальними аспектами вирішальне значення мають фінансові ресурси, що забезпечуватимуть досягнення миру та справедливості в контексті досягнення Цілей сталого розвитку (які підтримані Україною 2019 року). Саме тому метою цього науково-практичного дослідження є оцінка сучасних викликів у царині фінансового забезпечення миру та справедливості в Україні й обґрунтування практичних рекомендацій щодо вдосконалення механізму фінансового забезпечення, який би поєднував різні ефективні форми та інструменти фінансування.У результаті проведеного дослідження обґрунтована актуальна необхідність фінансування виконання завдань, передбачених досягненням 16 Цілі ЦСР, проаналізовано тенденції фінансування миру та справедливості за роки війни, оцінена визначальна роль міжнародної фінансової допомоги у фінансуванні досягнення 16 Цілі ЦСР та визначено величину фінансового шоку від можливого недоотримання міжнародної фінансової допомоги, левову частку якої спрямовують саме на досягнення цієї цілі. Доведено, що розмір фінансового шоку від нестабільності офіційної міжнародної фінансової допомоги прямо пропорційно впливає на фінансові можливості держави із забезпечення миру та справедливості в суспільстві, особливо в період активної фази війни. Автори обґрунтували заходи з диверсифікації фінансового забезпечення досягнення 16 Цілі ЦСР в Україні з метою зниження рівня можливого фінансового шоку від нерегулярності надходження офіційної міжнародної фінансової допомоги.

Deep learning architectures for supervised learning on tabular data range from simple multilayer perceptrons (MLP) to sophisticated Transformers and retrieval-augmented methods. This study highlights a major, yet so far overlooked opportunity for substantially improving tabular MLPs: namely, parameter-efficient ensembling -- a paradigm for implementing an ensemble of models as one model producing multiple predictions. We start by developing TabM -- a simple model based on MLP and our variations of BatchEnsemble (an existing technique). Then, we perform a large-scale evaluation of tabular DL architectures on public benchmarks in terms of both task performance and efficiency, which renders the landscape of tabular DL in a new light. Generally, we show that MLPs, including TabM, form a line of stronger and more practical models compared to attention- and retrieval-based architectures. In particular, we find that TabM demonstrates the best performance among tabular DL models. Lastly, we conduct an empirical analysis on the ensemble-like nature of TabM. For example, we observe that the multiple predictions of TabM are weak individually, but powerful collectively. Overall, our work brings an impactful technique to tabular DL, analyses its behaviour, and advances the performance-efficiency trade-off with TabM -- a simple and powerful baseline for researchers and practitioners.

Recently, Transformer-like deep architectures have shown strong performance on tabular data problems. Unlike traditional models, e.g., MLP, these architectures map scalar values of numerical features to high-dimensional embeddings before mixing them in the main backbone. In this work, we argue that embeddings for numerical features are an underexplored degree of freedom in tabular DL, which allows constructing more powerful DL models and competing with GBDT on some traditionally GBDT-friendly benchmarks. We start by describing two conceptually different approaches to building embedding modules: the first one is based on a piecewise linear encoding of scalar values, and the second one utilizes periodic activations. Then, we empirically demonstrate that these two approaches can lead to significant performance boosts compared to the embeddings based on conventional blocks such as linear layers and ReLU activations. Importantly, we also show that embedding numerical features is beneficial for many backbones, not only for Transformers. Specifically, after proper embeddings, simple MLP-like models can perform on par with the attention-based architectures. Overall, we highlight embeddings for numerical features as an important design aspect with good potential for further improvements in tabular DL.

The latent spaces of GAN models often have semantically meaningful directions. Moving in these directions corresponds to human-interpretable image transformations, such as zooming or recoloring, enabling a more controllable generation process. However, the discovery of such directions is currently performed in a supervised manner, requiring human labels, pretrained models, or some form of self-supervision. These requirements severely restrict a range of directions existing approaches can discover. In this paper, we introduce an unsupervised method to identify interpretable directions in the latent space of a pretrained GAN model. By a simple model-agnostic procedure, we find directions corresponding to sensible semantic manipulations without any form of (self-)supervision. Furthermore, we reveal several non-trivial findings, which would be difficult to obtain by existing methods, e.g., a direction corresponding to background removal. As an immediate practical benefit of our work, we show how to exploit this finding to achieve competitive performance for weakly-supervised saliency detection.

In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) -- an alternative design of GANs that can serve as a tool for generative model analysis. While the latent space of a typical GAN consists of input vectors, randomly sampled from the standard Gaussian distribution, the latent space of RPGAN consists of random paths in a generator network. As we show, this design allows to understand factors of variation, captured by different generator layers, providing their natural interpretability. With experiments on standard benchmarks, we demonstrate that RPGAN reveals several interesting insights about the roles that different layers play in the image generation process. Aside from interpretability, the RPGAN model also provides competitive generation quality and allows efficient incremental learning on new data.

Similarity graphs are an active research direction for the nearest neighbor search (NNS) problem. New algorithms for similarity graph construction are continuously being proposed and analyzed by both theoreticians and practitioners. However, existing construction algorithms are mostly based on heuristics and do not explicitly maximize the target performance measure, i.e., search recall. Therefore, at the moment it is not clear whether the performance of similarity graphs has plateaued or more effective graphs can be constructed with more theoretically grounded methods. In this paper, we introduce a new principled algorithm, based on adjacency matrix optimization, which explicitly maximizes search efficiency. Namely, we propose a probabilistic model of a similarity graph defined in terms of its edge probabilities and show how to learn these probabilities from data as a reinforcement learning task. As confirmed by experiments, the proposed construction method can be used to refine the state-of-the-art similarity graphs, achieving higher recall rates for the same number of distance computations. Furthermore, we analyze the learned graphs and reveal the structural properties that are responsible for more efficient search.

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently proposed, the overall quality of student samples is typically lower compared to the teacher ones, which hinders their practical usage. In this work, we investigate the relative quality of samples produced by the teacher text-to-image diffusion model and its distilled student version. As our main empirical finding, we discover that a noticeable portion of student samples exhibit superior fidelity compared to the teacher ones, despite the \"approximate\" nature of the student. Based on this finding, we propose an adaptive collaboration between student and teacher diffusion models for effective text-to-image synthesis. Specifically, the distilled model produces the initial sample, and then an oracle decides whether it needs further improvements with a slow teacher model. Extensive experiments demonstrate that the designed pipeline surpasses state-of-the-art text-to-image alternatives for various inference budgets in terms of human preference. Furthermore, the proposed approach can be naturally used in popular applications such as text-guided image editing and controllable generation.

Diffusion distillation represents a highly promising direction for achieving faithful text-to-image generation in a few sampling steps. However, despite recent successes, existing distilled models still do not provide the full spectrum of diffusion abilities, such as real image inversion, which enables many precise image manipulation methods. This work aims to enrich distilled text-to-image diffusion models with the ability to effectively encode real images into their latent space. To this end, we introduce invertible Consistency Distillation (iCD), a generalized consistency distillation framework that facilitates both high-quality image synthesis and accurate image encoding in only 3-4 inference steps. Though the inversion problem for text-to-image diffusion models gets exacerbated by high classifier-free guidance scales, we notice that dynamic guidance significantly reduces reconstruction errors without noticeable degradation in generation performance. As a result, we demonstrate that iCD equipped with dynamic guidance may serve as a highly effective tool for zero-shot text-guided image editing, competing with more expensive state-of-the-art alternatives.

Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical deployment. In this work, we analyze existing tabular benchmarks and find two common characteristics of tabular data in typical industrial applications that are underrepresented in the datasets usually used for evaluation in the literature. First, in real-world deployment scenarios, distribution of data often changes over time. To account for this distribution drift, time-based train/test splits should be used in evaluation. However, popular tabular datasets often lack timestamp metadata to enable such evaluation. Second, a considerable portion of datasets in production settings stem from extensive data acquisition and feature engineering pipelines. This can have an impact on the absolute and relative number of predictive, uninformative, and correlated features compared to academic datasets. In this work, we aim to understand how recent research advances in tabular deep learning transfer to these underrepresented conditions. To this end, we introduce TabReD -- a collection of eight industry-grade tabular datasets. We reassess a large number of tabular ML models and techniques on TabReD. We demonstrate that evaluation on time-based data splits leads to different methods ranking, compared to evaluation on random splits, which are common in current benchmarks. Furthermore, simple MLP-like architectures and GBDT show the best results on the TabReD datasets, while other methods are less effective in the new setting.