arXiv subjects

Juan Jose Garau-Luis

Publications and source records attributed to Juan Jose Garau-Luis.

7 recordsLinked to original sources

arXiv2024

Multi-modal Transfer Learning between Biological Foundation Models

Biological sequences encode fundamental instructions for the building blocks of life, in the form of DNA, RNA, and proteins. Modeling these sequences is key to understand disease mechanisms and is an active research area in computational biology. Recently, Large Language Models have shown great promise in solving certain biological tasks but current approaches are limited to a single sequence modality (DNA, RNA, or protein). Key problems in genomics intrinsically involve multiple modalities, but it remains unclear how to adapt general-purpose sequence models to those cases. In this work we propose a multi-modal model that connects DNA, RNA, and proteins by leveraging information from different pre-trained modality-specific encoders. We demonstrate its capabilities by applying it to the largely unsolved problem of predicting how multiple RNA transcript isoforms originate from the same gene (i.e. same DNA sequence) and map to different transcription expression levels across various human tissues. We show that our model, dubbed IsoFormer, is able to accurately predict differential transcript expression, outperforming existing methods and leveraging the use of multiple modalities. Our framework also achieves efficient transfer knowledge from the encoders pre-training as well as in between modalities. We open-source our model, paving the way for new multi-modal gene expression approaches.

cs.LG↗

arXiv2024

Dynamic Frequency Assignment for Mobile Users in Multibeam Satellite Constellations

Mobile users such as airplanes or ships will constitute an important segment of the future satellite communications market. Operators are now able to leverage digital payloads that allow flexible resource allocation policies that are robust against dynamic user bases. One of the key problems is managing the frequency spectrum efficiently, which has not been sufficiently explored for mobile users. To address this gap, we propose a dynamic frequency management algorithm based on linear programming that assigns resources in scenarios with both fixed and mobile users by combining long-term planning with real-time operation. We propose different strategies divided into proactive strategies, which stem from robust optimization practices, and reactive strategies, which exploit a high degree of real-time control. This represents a tradeoff between how conservative long-time planning should be and how much real-time reconfiguration is needed. To assess the performance of our method and to determine which proactive and reactive strategies work better under which context, we simulate operational use cases of non-geostationary constellations with different levels of dimensionality and uncertainty, showing that our method is able to serve over 99.97\% of the fixed and mobile users in scenarios with more than 900 beams. Finally, we discuss the trade-offs between the studied strategies in terms of the number of served users, power consumption, and number of changes that need to happen during operations.

cs.NI↗

arXiv2023

Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability

Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. Designing RL algorithms that optimize these objectives can be a costly and painstaking process. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions. MetaPG explicitly optimizes for generalizability and performance, and implicitly optimizes the stability of both metrics. We initialize our loss function population with Soft Actor-Critic (SAC) and perform multi-objective optimization using fitness metrics encoding single-task performance, zero-shot generalizability to unseen environment configurations, and stability across independent runs with different random seeds. On a set of continuous control tasks from the Real-World RL Benchmark Suite, we find that our method, using a single environment during evolution, evolves algorithms that improve upon SAC's performance and generalizability by 4% and 20%, respectively, and reduce instability up to 67%. Then, we scale up to more complex environments from the Brax physics simulator and replicate generalizability tests encountered in practical settings, such as different friction coefficients. MetaPG evolves algorithms that can obtain 10% better generalizability without loss of performance within the same meta-training environment and obtain similar results to SAC when doing cross-domain evaluations in other Brax environments. The evolution results are interpretable; by analyzing the structure of the best algorithms we identify elements that help optimizing certain objectives, such as regularization terms for the critic loss.

cs.LG↗

arXiv2022

Frequency Plan Design for Multibeam Satellite Constellations Using Linear Programming

Upcoming large satellite constellations and the advent of tighter steerable beams will offer unprecedented flexibility. This new flexibility will require resource management strategies to be operated in high-dimensional and dynamic environments, as existing satellite operators are unaccustomed to operational flexibility and automation. Frequency assignment policies have the potential to drive constellations' performance in this new context, and are no exception to real-time and scalability requirements. The majority of frequency assignment methods proposed in the literature fail to fulfill these two requirements, or are unable to meet them without falling short on bandwidth and/or power efficiency. In this paper we propose a new frequency assignment method designed to prioritize operational requirements. We present an algorithm based on Integer Linear Programming (ILP) that is able to fully define a frequency plan while respecting key system constraints such as handovers and interference. We are able to encode operators' goals such as bandwidth maximization or power reduction and produce optimal or quasi-optimal plans according to such objectives. In our experiments, we find our method is able to allocate at least 50% more bandwidth and reduce power consumption by 40% compared to previous operational benchmarks. The performance advantage of our method compared to previous solutions increases with the dimensionality of the constellation; in an experiment with a 5,000-beam MEO constellation we find that we can allocate three times more bandwidth.

cs.CE↗

arXiv2021

Towards Autonomous Satellite Communications: An AI-based Framework to Address System-level Challenges

The next generation of satellite constellations is designed to better address the future needs of our connected society: highly-variable data demand, mobile connectivity, and reaching more under-served regions. Artificial Intelligence (AI) and learning-based methods are expected to become key players in the industry, given the poor scalability and slow reaction time of current resource allocation mechanisms. While AI frameworks have been validated for isolated communication tasks or subproblems, there is still not a clear path to achieve fully-autonomous satellite systems. Part of this issue results from the focus on subproblems when designing models, instead of the necessary system-level perspective. In this paper we try to bridge this gap by characterizing the system-level needs that must be met to increase satellite autonomy, and introduce three AI-based components (Demand Estimator, Offline Planner, and Real Time Engine) that jointly address them. We first do a broad literature review on the different subproblems and identify the missing links to the system-level goals. In response to these gaps, we outline the three necessary components and highlight their interactions. We also discuss how current models can be incorporated into the framework and possible directions of future work.

cs.AI↗

arXiv2021

Integrating LSTMs and GNNs for COVID-19 Forecasting

The spread of COVID-19 has coincided with the rise of Graph Neural Networks (GNNs), leading to several studies proposing their use to better forecast the evolution of the pandemic. Many such models also include Long Short Term Memory (LSTM) networks, a common tool for time series forecasting. In this work, we further investigate the integration of these two methods by implementing GNNs within the gates of an LSTM and exploiting spatial information. In addition, we introduce a skip connection which proves critical to jointly capture the spatial and temporal patterns in the data. We validate our daily COVID-19 new cases forecast model on data of 37 European nations for the last 472 days and show superior performance compared to state-of-the-art graph time series models based on mean absolute scaled error (MASE). This area of research has important applications to policy-making and we analyze its potential for pandemic resource control.

cs.LG↗

arXiv2021

Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research

Deep Reinforcement Learning (DRL) is considered a potential framework to improve many real-world autonomous systems; it has attracted the attention of multiple and diverse fields. Nevertheless, the successful deployment in the real world is a test most of DRL models still need to pass. In this work we focus on this issue by reviewing and evaluating the research efforts from both domain-agnostic and domain-specific communities. On one hand, we offer a comprehensive summary of DRL challenges and summarize the different proposals to mitigate them; this helps identifying five gaps of domain-agnostic research. On the other hand, from the domain-specific perspective, we discuss different success stories and argue why other models might fail to be deployed. Finally, we take up on ways to move forward accounting for both perspectives.

cs.LG↗