HSE Scientists Optimise Training of Generative Flow Networks
Researchers at the HSE Faculty of Computer Science have optimised the training method for generative flow neural networks to handle unstructured tasks, which could make the search for new drugs more efficient. The results of their work were presented at ICLR 2025, one of the world’s leading conferences on machine learning. The paper is available at Arxiv.org.
Generative Flow Networks (GFlowNets) are a class of machine learning algorithms that build complex objects step by step. Researchers use them to search for new proteins and drugs, and to optimise transport systems.
For GFlowNets to discover such complex structures, researchers specify the desired properties of the target object. The closer the network’s proposed solution is to these properties, the higher the reward it receives. GFlowNets aim to solve problems in a way that maximises their reward. They do not rely on data directly, but instead on the reward, which is computed using an equation known as the value function.
The search for a complex object can be compared to assembling a Lego model, where pieces are added step by step until the object is complete, with each model assigned a specific value—for example, a plant model might be valued higher than an animal model. Unlike other machine learning methods that would strive to construct a plant at any cost, GFlowNets generate a variety of objects—but plants more frequently than animals—because the reward for plants is higher.
In this type of search, GFlowNets rely on two stochastic policies that operate together: a forward policy and a backward policy. The forward policy can be thought of as a construction foreman, deciding the next step and estimating the probability of the subsequent state, while the backward policy acts as a deconstruction expert, identifying the preceding step. Maintaining balance between these flows is crucial but difficult to achieve. First, it requires significant computing power. Second, backward policies lack flexibility: researchers usually prevent them from adapting during the search or from observing the actions of the forward policy.
HSE scientists have developed a way to optimise backward policies using a method called Trajectory Likelihood Maximisation (TLM). They refined the backward policy’s algorithms so that it can be continuously checked against the steps of the forward policy.
'We designed the search for the optimal solution to resemble a negotiation, where both sides are ready to adjust their positions. In highly uncertain problems, the backward policy serves only as an auxiliary tool that improves the results of the forward policy. Our goal was to make the backward policy more flexible, and we finally succeeded,' explains Timofey Gritsaev, co-author of the paper and Research Assistant of the Centre for Deep Learning and Bayesian Methods at the HSE FCS AI and Digital Science Institute.
After implementing TLM, the reward function that measures the backward model’s success became more complex. Nevertheless, despite this increased complexity, the overall search system became faster and more efficient.
'Our method explores the space of possible solutions noticeably faster and identifies more high-quality options. Overall, this approach brings generative models closer to reinforcement learning methods,' explains Nikita Morozov, Junior Research Fellow of the Centre for Deep Learning and Bayesian Methods at the AI and Digital Science Institute of the HSE FCS.
The authors of the study are confident that their work will benefit specialists using GFlowNets across various fields, including the search for new medicinal compounds, the development of materials with specific properties, and the fine-tuning of large language models. Thanks to these networks’ ability to efficiently explore vast solution spaces and quickly identify the best options, the demand on computing power can be significantly reduced.
See also:
Physicists Propose New Mechanism to Enhance Superconductivity with 'Quantum Glue'
A team of researchers, including scientists from HSE MIEM, has demonstrated that defects in a material can enhance, rather than hinder, superconductivity. This occurs through interaction between defective and cleaner regions, which creates a 'quantum glue'—a uniform component that binds distinct superconducting regions into a single network. Calculations confirm that this mechanism could aid in developing superconductors that operate at higher temperatures. The study has been published in Communications Physics.
Neural Network Trained to Predict Crises in Russian Stock Market
Economists from HSE University have developed a neural network model that can predict the onset of a short-term stock market crisis with over 83% accuracy, one day in advance. The model performs well even on complex, imbalanced data and incorporates not only economic indicators but also investor sentiment. The paper by Tamara Teplova, Maksim Fayzulin, and Aleksei Kurkin from the Centre for Financial Research and Data Analytics at the HSE Faculty of Economic Sciences has been published in Socio-Economic Planning Sciences.
Larger Groups of Students Use AI More Effectively in Learning
Researchers at the Institute of Education and the Faculty of Economic Sciences at HSE University have studied what factors determine the success of student group projects when they are completed with the help of artificial intelligence (AI). Their findings suggest that, in addition to the knowledge level of the team members, the size of the group also plays a significant role—the larger it is, the more efficient the process becomes. The study was published in Innovations in Education and Teaching International.
New Models for Studying Diseases: From Petri Dishes to Organs-on-a-Chip
Biologists from HSE University, in collaboration with researchers from the Kulakov National Medical Research Centre for Obstetrics, Gynecology, and Perinatology, have used advanced microfluidic technologies to study preeclampsia—one of the most dangerous pregnancy complications, posing serious risks to the life and health of both mother and child. In a paper published in BioChip Journal, the researchers review modern cellular models—including advanced placenta-on-a-chip technologies—that offer deeper insights into the mechanisms of the disorder and support the development of effective treatments.
Advancing Personalised Therapy for More Effective Cancer Treatment
Researchers from the International Laboratory of Microphysiological Systems at HSE University's Faculty of Biology and Biotechnology are developing methods to reduce tumour cell resistance to drugs and to create more effective, personalised cancer treatments. In this interview with the HSE News Service, Diana Maltseva, Head of the Laboratory, talks about their work.
Solvent Instead of Toxic Reagents: Chemists Develop Environmentally Friendly Method for Synthesising Aniline Derivatives
An international team of researchers, including chemists from HSE University and the A.N. Nesmeyanov Institute of Organoelement Compounds of the Russian Academy of Sciences (INEOS RAS), has developed a new method for synthesising aniline derivatives—compounds widely used in the production of medicines, dyes, and electronic materials. Instead of relying on toxic and expensive reagents, they proposed using tetrahydrofuran, which can be derived from renewable raw materials. The reaction was carried out in the presence of readily available cobalt salts and syngas. This approach reduces hazardous waste and simplifies the production process, making it more environmentally friendly. The study has been published in ChemSusChem.
Quantity over Quality: How Publication Activity Leads to Crisis
Participants of the 4th Fall into ML conference at HSE University held a discussion titled ‘Academia in Crisis: What Does the Future Hold?’ In particular, they examined why the number of scientific publications continues to grow, what the quality of these papers is, what expectations should be placed on researchers, and what role artificial intelligence plays in preparing academic articles.
Master’s Students of HSE, University of Campinas, and Tsinghua University Publish Joint Student Research Collection
Master’s students of the HSE ISSEK programme ‘Science, Technology and Innovation Management and Policy’ have released a joint research collection with the University of Campinas (Brazil) and Tsinghua University (China) titled ‘Being Innovative or Being on the Safe Side—Managing the Risk of Failure.’ The authors explore how organisations perceive risks and embrace innovation within different cultural contexts.
‘A Turn Away from Stereotypes’: Moscow Hosts ‘Researching the Deaf Community’ Conference
On October 17–19, 2025, the third annual interdisciplinary conference ‘Researching the Deaf Community 2025: on the Periphery of Attention’ took place at GES-2 House of Culture in Moscow. The event was organised with the participation of the HSE International Laboratory for Social Integration Research. HSE University Vice Rector Irina Martusevich addressed attendees at the opening ceremony.
Exploring the Mind: HSE Scientists Discuss Cognitive Technologies of the Future
Why we make irrational decisions, how the brain responds to fakes, and whether neural networks are capable of thinking—these were the topics discussed by early-career scientists of HSE University during the NAUKA 0+ science festival. The event brought together students and experts from various fields, united by a common goal—to deepen their understanding of the human brain and cognitive technologies.