Aalto computer scientists in ICML 2025
International Conference on Machine Learning (ICML) is one of the premier gatherings for professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics.
The Forty-Second International Conference on Machine Learning is held on July 13th - July 19th, 2025 in Vancouver Convention Center, Canada.
Accepted papers
In alphabetical order. Click the title to see the authors and the abstract.
Authors
Mehmet Yiğit Balık, Maksim Sinelnikov, Priscilla Ong, and Harri Lähdesmäki
Abstract
High-dimensional time-series datasets are common in domains such as healthcare and economics. Variational autoencoder (VAE) models, where latent variables are modeled with a Gaussian process (GP) prior, have become a prominent model class to analyze such correlated datasets. However, their applications are challenged by the inherent cubic time complexity that requires specific GP approximation techniques, as well as the general challenge of modeling both shared and individual-specific correlations across time. Though inducing points enhance GP prior VAE scalability, optimizing them remains challenging, especially since discrete covariates resist gradient‑based methods. In this work, we propose a scalable basis function approximation technique for GP prior VAEs that mitigates these challenges and results in linear time complexity, with a global parametrization that eliminates the need for amortized variational inference and the associated amortization gap, making it well-suited for conditional generation tasks where accuracy and efficiency are crucial. Empirical evaluations on synthetic and real-world benchmark datasets demonstrate that our approach not only improves scalability and interpretability but also drastically enhances predictive performance.
Authors
Rafał Karczewski, Markus Heinonen, and Vikas Garg
Abstract
Diffusion models have emerged as a powerful class of generative models, capable of producing high-quality images by mapping noise to a data distribution. However, recent findings suggest that image likelihood does not align with perceptual quality: high-likelihood samples tend to be smooth, while lower-likelihood ones are more detailed. Controlling sample density is thus crucial for balancing realism and detail. In this paper, we analyze an existing technique, Prior Guidance, which scales the latent code to influence image detail. We introduce score alignment, a condition that explains why this method works and show that it can be tractably checked for any continuous normalizing flow model. We then propose Density Guidance, a principled modification of the generative ODE that enables exact log-density control during sampling. Finally, we extend Density Guidance to stochastic sampling, ensuring precise log-density control while allowing controlled variation in structure or fine details. Our experiments demonstrate that these techniques provide fine-grained control over image detail without compromising sample quality. Code is available at https://github.com/Aalto-QuML/density-guidance.
Authors
Corinna Coupette, Jeremy Wayland, Emily Simons, and Bastian Rieck
Abstract
Benchmark datasets have proved pivotal to the success of graph learning, and good benchmark datasets are crucial to guide the development of the field. Recent research has highlighted problems with graph-learning datasets and benchmarking practices—revealing, for example, that methods which ignore the graph structure can outperform graph-based approaches on popular benchmark datasets. Such findings raise two questions: (1) What makes a good graph-learning dataset, and (2) how can we evaluate dataset quality in graph learning? Our work addresses these questions. As the classic evaluation setup uses datasets to evaluate models, it does not apply to dataset evaluation. Hence, we start from first principles. Observing that graph-learning datasets uniquely combine two modes—the graph structure and the node features—, we introduce RINGS, a flexible and extensible mode-perturbation framework to assess the quality of graph-learning datasets based on dataset ablations—i.e., by quantifying differences between the original dataset and its perturbed representations. Within this framework, we propose two measures—performance separability and mode complementarity—as evaluation tools, each assessing, from a distinct angle, the capacity of a graph dataset to benchmark the power and efficacy of graph-learning methods. We demonstrate the utility of our framework for graph-learning dataset evaluation in an extensive set of experiments and derive actionable recommendations for improving the evaluation of graph-learning methods. Our work opens new research directions in data-centric graph learning, and it constitutes a first step toward the systematic evaluation of evaluations.
Authors
Yogesh Verma, Amauri Souza, and Vikas Garg
Abstract
The local inductive bias of message-passing graph neural networks (GNNs) hampers their ability to exploit key structural information (e.g., connectivity and cycles). Positional encoding (PE) and Persistent Homology (PH) have emerged as two promising approaches to mitigate this issue. PE schemes endow GNNs with location-aware features, while PH methods enhance GNNs with multiresolution topological features. However, a rigorous theoretical characterization of the relative merits and shortcomings of PE and PH has remained elusive. We bridge this gap by establishing that neither paradigm is more expressive than the other, providing novel constructions where one approach fails but the other succeeds. Our insights inform the design of a novel learnable method, PiPE (Persistence-informed Positional Encoding), which is provably more expressive than both PH and PE. PiPE demonstrates strong performance across a variety of tasks (e.g., molecule property prediction, graph classification, and out-of-distribution generalization), thereby advancing the frontiers of graph representation learning. Code is available at https://github.com/Aalto-QuML/PIPE
Authors
Severi Rissanen, RuiKang OuYang, Jiajun He, Wenlin Chen, Markus Heinonen, Arno Solin, and Jose Miguel Hernandez-Lobato
Abstract
Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel Tempering (PT), when it comes to the efficiency of target evaluations. On the other hand, unlike a well-trained neural sampler, PT yields only dependent samples and needs to be rerun---at considerable computational cost---whenever new samples are required. To address these weaknesses, we propose the Progressive Tempering Sampler with Diffusion (PTSD), which trains diffusion models sequentially across temperatures, leveraging the advantages of PT to improve the training of neural samplers. We also introduce a novel method to combine high-temperature diffusion models to generate approximate lower-temperature samples, which are minimally refined using MCMC and used to train the next diffusion model. PTSD enables efficient reuse of sample information across temperature levels while generating well-mixed, uncorrelated samples. Our method significantly improves target evaluation efficiency,outperforming diffusion-based neural samplers.
Accepted papers 2024
ICML 2024 was held in Wien, Austria on 21-27 July, 2024.
Authors
Maksim Sinelnikov, Manuel Haussmann, Harri Lähdesmäki
Abstract
Longitudinal data are important in numerous fields, such as healthcare, sociology and seismology, but real-world datasets present notable challenges for practitioners because they can be high-dimensional, contain structured missingness patterns, and measurement time points can be governed by an unknown stochastic process. While various solutions have been suggested, the majority of them have been designed to account for only one of these challenges. In this work, we propose a flexible and efficient latent-variable model that is capable of addressing all these limitations. Our approach utilizes Gaussian processes to capture temporal correlations between samples and their associated missingness masks as well as to model the underlying point process. We construct our model as a variational autoencoder together with deep neural network parameterised encoder and decoder models, and develop a scalable amortised variational inference approach for efficient model training. We demonstrate competitive performance using both simulated and real datasets.
Department of Computer Science
We are an internationally-oriented community and home to world-class research in modern computer science.
School of Science
Science for tomorrow’s technology, innovations and businesses
Read more news
The TAIMI project builds an equal working life – a six-year consortium project seeks solutions to recruitment and skill challenges
Artificial intelligence (AI) is changing skill requirements, the population is aging, and the labor shortage is deepening. Meanwhile, the potential of international experts often remains unused in Finland. These challenges in working life are addressed by the six-year TAIMI project funded by the Strategic Research Council, and implemented by a broad consortium.
Unite! Seed Fund 2026: Call opens on 20 January 2026
Gain an early overview of the Unite! Seed Fund Call of Spring 2026. The call includes three funding lines: Student Activities, Teaching and Learning, and Research and PhD.
Deepika Yadav leverages technology to improve women's health
Deepika Yadav recently began as an assistant professor at the Department of Computer Science in the field of human-computer interaction (HCI) and interaction design for health and wellbeing.