Samuel Kaski

• D.Sc.
• Professor at Aalto University

Preferential Bayesian Optimization (PBO) is a sample-efficient method to learn latent user utilities from preferential feedback over a pair of designs. It relies on a statistical surrogate model for the latent function, usually a Gaussian process, and an acquisition strategy to select the next candidate pair to get user feedback on. Due to the non-...

Selection of efficient multi-step synthesis routes is a fundamental challenge in organic synthesis. Comparing different routes involves numerous parameters, economic considerations, and integration of nuanced chemical knowledge. While computer-aided synthesis planning (CASP) tools can generate synthetic routes, evaluating their overall feasibility...

Selection of efficient multi-step synthesis routes is a fundamental challenge in organic synthesis. Comparing different routes involves numerous parameters, economic considerations, and integration of nuanced chemical knowledge. While computer-aided synthesis planning (CASP) tools can generate synthetic routes, evaluating their overall feasibility...

As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks through experience remains a key challenge. Current LLM agents, particularly those based on proprietary language models, typically rely on prompts to incorporate knowledge about the target tasks. This approa...

Assay interference caused by small organic compounds continues to pose formidable challenges to early drug discovery. Various computational methods have been developed to identify compounds likely to cause assay interference. However, due to the scarcity of data available for model development, the predictive accuracy and applicability of these app...

Health registers contain rich information about individuals' health histories. Here our interest lies in understanding how individuals' health trajectories evolve in a nationwide longitudinal dataset with coded features, such as clinical codes, procedures, and drug purchases. We introduce a straightforward approach for training a Transformer-based...

Machine learning (ML) systems have enabled the modelling of quantitative structure–property relationships (QSPR) and structure-activity relationships (QSAR) using existing experimental data to predict target properties for new molecules. These property predictors hold significant potential in accelerating drug discovery by guiding generative artifi...

The selection of efficient multi-step synthesis routes is a fundamental challenge in organic synthesis. Comparing different routes involves numerous parameters, economic considerations, and the integration of nuanced chemical knowledge. While computer-aided synthesis planning (CASP) tools can generate synthetic routes, evaluating their overall feas...

Generalization outside the scope of one's training data requires leveraging prior knowledge about the effects that transfer, and the effects that don't, between different data sources. Bayesian transfer learning is a principled paradigm for specifying this knowledge, and refining it on the basis of data from the source (training) and target (predic...

Many critical decisions, such as personalized medical diagnoses and product pricing, are made based on insights gained from designing, observing, and analyzing a series of experiments. This highlights the crucial role of experimental design, which goes beyond merely collecting information on system parameters as in traditional Bayesian experimental...

Amortized meta-learning methods based on pre-training have propelled fields like natural language processing and vision. Transformer-based neural processes and their variants are leading models for probabilistic meta-learning with a tractable objective. Often trained on synthetic data, these models implicitly capture essential latent information in...

Simulation-based inference (SBI) is the preferred framework for estimating parameters of intractable models in science and engineering. A significant challenge in this context is the large computational cost of simulating data from complex models, and the fact that this cost often depends on parameter values. We therefore propose \textit{cost-aware...

In recent years, there has been growing interest in leveraging human preferences for drug discovery to build models that capture chemists’ intuition for de novo molecular design, lead optimization, and prioritization for experimental validation. However, existing models derived from human preferences in chemistry are often black-boxes, lacking inte...

In drug discovery, prioritizing compounds for testing is an important task. Active learning can assist in this endeavor by prioritizing molecules for label acquisition based on their estimated potential to enhance in-silico models. However, in specialized cases like toxicity modeling, limited dataset sizes can hinder effective training of modern ne...

Drug-induced liver injury (DILI) presents a multifaceted challenge, influenced by interconnected biological mechanisms. Current DILI datasets are characterized by small sizes and high imbalance, posing difficulties in learning robust representations and accurate modeling. To address these challenges, we trained a multi-modal multi-task model integr...

Machine learning (ML) systems have enabled the modelling of quantitative structure-property relationships (QSPR) and structure-activity relationships (QSAR) using existing experimental data to predict target properties for new molecules. These property predictors hold significant potential in accelerating drug discovery by guiding generative artifi...

New scientific knowledge is needed more urgently than ever, to address global challenges such as climate change, sustainability, health, and societal well-being. Could artificial intelligence (AI) accelerate science to meet these global challenges in time? AI is already revolutionizing individual scientific disciplines, but we argue here that it co...

One challenge that current de novo drug design models face is a disparity between the user’s expectations and the actual output of the model in practical applications. Tailoring models to better align with chemists’ implicit knowledge, expectation and preferences is key to overcoming this obstacle effectively. While interest in preference-based and...

Several generative models with elaborate training and sampling procedures have been proposed recently to accelerate structure-based drug design (SBDD); however, perplexingly, their empirical performance turns out to be suboptimal. We seek to better understand this phenomenon from both theoretical and empirical perspectives. Since most of these mode...

Machine learning (ML) systems have enabled the modelling of quantitative structure-property relationships (QSPR) and structure-activity relationships (QSAR) using existing experimental data to predict target properties for new molecules. These property predictors hold significant potential in accelerating drug discovery by guiding generative artifi...

Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to those corruptions but may harm performance on clean images and other types of distortion. In this paper, we introduce an alternative approach that improves the robustnes...

Background Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible due to privacy concerns and parties are unable to engage in centrally coordinated joint computation. We study the feasibility of combining privacy preserving synthe...

GFlowNets are a promising alternative to MCMC sampling for discrete compositional random variables. Training GFlowNets requires repeated evaluations of the unnormalized target distribution or reward function. However, for large-scale posterior sampling, this may be prohibitive since it incurs traversing the data several times. Moreover, if the data...

Preferential Bayesian optimization (PBO) is a sample-efficient framework for learning human preferences between candidate designs. PBO classically relies on homoscedastic noise models to represent human aleatoric uncertainty. Yet, such noise fails to accurately capture the varying levels of human aleatoric uncertainty, particularly when the user po...

Current de novo drug design models face one crucial challenge: a disparity between the user’s expectations and the actual output of the model in practical applications. Tailoring models to better align with chemists’ preferences is key to overcoming this obstacle effectively. While interest in preference-based and human-in-the-loop machine learning...

Recent magnetoencephalography (MEG) studies have reported that functional connectivity (FC) and power spectra can be used as neural fingerprints in differentiating individuals. Such studies have mainly used correlations between measurement sessions to distinguish individuals from each other. However, it has remained unclear whether such correlation...

Our digital life consists of activities that are organized around tasks and exhibit different user states in the digital contexts around these activities. Previous works have shown that digital activity monitoring can be used to predict entities that users will need to perform digital tasks. There have been methods developed to automatically detect...

More than 10 million Europeans show signs of mild cognitive impairment (MCI), a transitional stage between normal brain aging and dementia stage memory disorder. The path MCI takes can be divergent; while some maintain stability or even revert to cognitive norms, alarmingly, up to half of the cases progress to dementia within 5 years. Current diagn...

Randomized controlled trials (RCTs) are the accepted standard for treatment effect estimation but they can be infeasible due to ethical reasons and prohibitive costs. Single-arm trials, where all patients belong to the treatment group, can be a viable alternative but require access to an external control group. We propose an identifiable deep laten...

Likelihood-free inference (LFI) has been successfully applied to state-space models, where the likelihood of observations is not available but synthetic observations generated by a black-box simulator can be used for inference instead. However, much of the research up to now has been restricted to cases in which a model of state transition dynamics...

The problem of model selection with a limited number of experimental trials has received considerable attention in cognitive science, where the role of experiments is to discriminate between theories expressed as computational models. Research on this subject has mostly been restricted to optimal experiment design with analytically tractable models...

We introduce a cooperative Bayesian optimization problem for optimizing black-box functions of two variables where two agents choose together at which points to query the function but have only control over one variable each. This setting is inspired by human-AI teamwork, where an AI-assistant helps its human user solve a problem, in this simplest...

Recent magnetoencephalography (MEG) studies have reported that functional connectivity (FC) and power spectra can be used as neural fingerprints in differentiating individuals. Such studies have mainly used correlations between measurement sessions to distinguish individuals from each other. However, it has remained unclear whether such correlation...

Motivation: Existing methods for simulating synthetic genotype and phenotype datasets have limited scalability, constraining their usability for large-scale analyses. Moreover, a systematic approach for evaluating synthetic data quality and a benchmark synthetic dataset for developing and evaluating methods for polygenic risk scores are lacking....

Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible. We propose a framework in which each party shares a differentially private synthetic twin of their data. We study the feasibility of combining such synthetic twin data sets f...

Drug-induced liver injury (DILI) is an important safety concern and a major reason to remove a drug from the market. Advancements in recent machine learning methods have led to a wide range of in silico models for DILI predictive methods based on molecule chemical structures (fingerprints). Existing publicly available DILI data sets used for model...

Large-scale networks of phase synchronization are considered to regulate the communication between brain regions fundamental to cognitive function, but the mapping to their structural substrates, i.e., the structure-function relationship, remains poorly understood. Biophysical Network Models (BNMs) have demonstrated the influences of local oscillat...

In sequential machine teaching, a teacher’s objective is to provide the optimal sequence of inputs to sequential learners in order to guide them towards the best model. However, this teaching objective considers a restricted class of learners with fixed inductive biases. In this paper, we extend the machine teaching framework to learners that can i...

We consider the problem of creating assistants that can help agents solve new sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant. Instead of acting in place of the agent as in current automation-based approaches, we give the assistant an advisory role and keep the agent in the loo...

Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as spatio-temporal modeling, Bayesian Optimization and continuous control, contain equivariances -- for example to translation...

Deep Ensembles (DEs) demonstrate improved accuracy, calibration and robustness to perturbations over single neural networks partly due to their functional diversity. Particle-based variational inference (ParVI) methods enhance diversity by formalizing a repulsion term based on a network similarity kernel. However, weight-space repulsion is ineffici...

Simulation-based inference (SBI) methods such as approximate Bayesian computation (ABC), synthetic likelihood, and neural posterior estimation (NPE) rely on simulating statistics to infer parameters of intractable likelihood models. However, such methods are known to yield untrustworthy and misleading inference outcomes under model misspecification...

Contextual Bayesian Optimization (CBO) is a powerful framework for optimizing black-box, expensive-to-evaluate functions with respect to design variables, while simultaneously efficiently integrating relevant contextual information regarding the environment, such as experimental conditions. However, in many practical scenarios, the relevance of con...

Family history is considered a risk factor for many diseases because it implicitly captures shared genetic, environmental and lifestyle factors. A nationwide electronic health record (EHR) system spanning multiple generations presents new opportunities for studying a connected network of medical histories for entire families. In this work we presen...

Modeling has actively tried to take the human out of the loop, originally for objectivity and recently also for automation. We argue that an unnecessary side effect has been that modeling workflows and machine learning pipelines have become restricted to only well-specified problems. Putting the humans back into the models would enable modeling a b...

Large-scale networks of phase synchronization are considered to regulate the communication between brain regions fundamental to cognitive function, but the mapping to their structural substrates, i.e. , the structure-function relationship, remains poorly understood. Biophysical Network Models (BNMs) have demonstrated the influences of local oscilla...

We need to rethink how we assist designers with artificial intelligence (AI). AI should aim to cooperate, not automate, by supporting and leveraging the creativity and problem‐solving capabilities of designers. The challenge for such AI is how to infer designers' goals and then help them without being needlessly disruptive. We introduce AI‐assisted...

The problem of model selection with a limited number of experimental trials has received considerable attention in cognitive science, where the role of experiments is to discriminate between theories expressed as computational models. Research on this subject has mostly been restricted to optimal experiment design with analytically tractable models...

A natural solution concept for many multiagent settings is the Stackelberg equilibrium, under which a ``leader'' agent selects a strategy that maximizes its own payoff assuming the ``follower'' chooses their best response to this strategy. Recent work has presented asymmetric learning updates that can be shown to converge to the \textit{differentia...

Likelihood-free inference methods typically make use of a distance between simulated and real data. A common example is the maximum mean discrepancy (MMD), which has previously been used for approximate Bayesian computation, minimum distance estimation, generalised Bayesian inference, and within the nonparametric learning framework. The MMD is comm...

A de novo molecular design workflow can be used together with technologies such as reinforcement learning to navigate the chemical space. A bottleneck in the workflow that remains to be solved is how to integrate human feedback in the exploration of the chemical space to optimize molecules. A human drug designer still needs to design the goal, expr...

Existing methods for simulating synthetic genotype and phenotype datasets have limited scalability, constraining their usability for large-scale analyses. Moreover, a systematic approach for evaluating synthetic data quality and a benchmark synthetic dataset for developing and evaluating methods for polygenic risk scores are lacking. We present HAP...

Background A deep understanding of carcinogenesis at the DNA level underpins many advances in cancer prevention and treatment. Mutational signatures provide a breakthrough conceptualisation, as well as an analysis framework, that can be used to build such understanding. They capture somatic mutation patterns and at best identify their causes. Most...

Neighbor embedding (NE) aims to preserve pairwise similarities between data items and has been shown to yield an effective principle for data visualization. However, even the best existing NE methods such as stochastic neighbor embedding (SNE) may leave large-scale patterns hidden, for example clusters, despite strong signals being present in the d...

The extent to which genetic interactions affect observed phenotypes is generally unknown because current interaction detection approaches only consider simple interactions between top SNPs of genes. We introduce an open-source framework for increasing the power of interaction detection by considering all SNPs within a selected set of genes and comp...

Different neuroimaging methods can yield different views of task-dependent neural engagement. Studies examining the relationship between electromagnetic and hemodynamic measures have revealed correlated patterns across brain regions but the role of the applied stimulation or experimental tasks in these correlation patterns is still poorly understoo...

Differentially private (DP) release of multidimensional statistics typically considers an aggregate sensitivity, e.g. the vector norm of a high-dimensional vector. However, different dimensions of that vector might have widely different magnitudes and therefore DP perturbation disproportionately affects the signal across dimensions. We observe this...

Bayesian optimization (BO) is a powerful framework for optimizing black-box, expensive-to-evaluate functions. Over the past decade, many algorithms have been proposed to integrate cheaper, lower-fidelity approximations of the objective function into the optimization process, with the goal of converging towards the global optimum at a reduced cost....

Approximate Bayesian computation (ABC) has advanced in two decades from a seminal idea to a practically applicable inference tool for simulator‐based statistical models, which are becoming increasingly popular in many research domains. The computational feasibility of ABC for practical applications has been recently boosted by adopting techniques f...

Generating new molecules is fundamental to advancing critical applications such as drug discovery and material synthesis. Flows can generate molecules effectively by inverting the encoding process, however, existing flow models either require artifactual dequantization or specific node/edge orderings, lack desiderata such as permutation invariance,...

Bayesian optimization (BO) is a well-established method to optimize black-box functions whose direct evaluations are costly. In this paper, we tackle the problem of incorporating expert knowledge into BO, with the goal of further accelerating the optimization, which has received very little attention so far. We design a multi-task learning architec...

p>New scientific knowledge is needed more urgently than ever, to address global challenges such as climate change, sustainability, health and societal well-being. Could artificial intelligence (AI) accelerate the scientific process to meet global challenges in time? AI is already revolutionizing individual scientific disciplines, but we argue here...

p>New scientific knowledge is needed more urgently than ever, to address global challenges such as climate change, sustainability, health and societal well-being. Could artificial intelligence (AI) accelerate the scientific process to meet global challenges in time? AI is already revolutionizing individual scientific disciplines, but we argue here...

A de novo molecular design workflow can be used together with technologies such as reinforcement learning to navigate the chemical space. A bottleneck in the workflow that remains to be solved is how to integrate human feedback in the exploration of the chemical space to optimize molecules. A human drug designer still needs to design the goal, expr...

Bayesian neural networks (BNNs) promise improved generalization under covariate shift by providing principled probabilistic representations of epistemic uncertainty. However, weight-based BNNs often struggle with high computational complexity of large-scale architectures and datasets. Node-based BNNs have recently been introduced as scalable altern...

While generation of synthetic data under differential privacy (DP) has received a lot of attention in the data privacy community, analysis of synthetic data has received much less. Existing work has shown that simply analysing DP synthetic data as if it were real does not produce valid inferences of population-level quantities. For example, confide...

Surrogate models have been successfully used in likelihood-free inference to decrease the number of simulator evaluations. The current state-of-the-art performance for this task has been achieved by Bayesian Optimization with Gaussian Processes (GPs). While this combination works well for unimodal target distributions, it is restricting the flexibi...

Centaurs are half-human, half-AI decision-makers where the AI's goal is to complement the human. To do so, the AI must be able to recognize the goals and constraints of the human and have the means to help them. We present a novel formulation of the interaction between the human and the AI as a sequential game where the agents are modelled using Ba...

We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees. d3p achieves general applicability to a wide range of probabilistic modelling problems by implementing the differentially private variational inference algorithm, allowing users to fit any parame...

Embarrassingly parallel Markov Chain Monte Carlo (MCMC) exploits parallel computing to scale Bayesian inference to large datasets by using a two-step approach. First, MCMC is run in parallel on (sub)posteriors defined on data partitions. Then, a server combines local results. While efficient, this framework is very sensitive to the quality of subpo...

We consider the problem of creating assistants that can help agents - often humans - solve novel sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant. Instead of aiming to automate, and act in place of the agent as in current approaches, we give the assistant an advisory role and ke...

Approximate Bayesian computation (ABC) is a popular likelihood-free inference method for models with intractable likelihood functions. As ABC methods usually rely on comparing summary statistics of observed and simulated data, the choice of the statistics is crucial. This choice involves a trade-off between loss of information and dimensionality re...

Approximate Bayesian computation (ABC) has advanced in two decades from a seminal idea to a practically applicable inference tool for simulator-based statistical models, which are becoming increasingly popular in many research domains. The computational feasibility of ABC for practical applications has been recently boosted by adopting techniques f...

Specification of the prior distribution for a Bayesian model is a central part of the Bayesian workflow for data analysis, but it is often difficult even for statistical experts. Prior elicitation transforms domain knowledge of various kinds into well-defined prior distributions, and offers a solution to the prior specification problem, in principl...

Phenotype prediction is a necessity in numerous applications in genetics. However, when the size of the individual-level data of the cohort of interest is small, statistical learning algorithms, from linear regression to neural networks, usually fail due to insufficient data. Fortunately, summary statistics from genome-wide association studies (GWA...

We introduce a method for inferring and predicting latent states in the important and difficult case of state-space models where observations can only be simulated, and transition dynamics are unknown. In this setting, the likelihood of observations is not available and only synthetic observations can be generated from a black-box simulator. We pro...

In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy by adding noise at the user's end. Thus, clients need not rely on the trustworthiness of the aggregator. In this work, we provide...

Approximate Bayesian inference estimates descriptors of an intractable target distribution - in essence, an optimization problem within a family of distributions. For example, Langevin dynamics (LD) extracts asymptotically exact samples from a diffusion process because the time evolution of its marginal distributions constitutes a curve that minimi...

Recommender systems can support everyday digital tasks by retrieving and recommending useful information contextually. This is becoming increasingly relevant in services and operating systems. Previous research often focuses on specific recommendation tasks with data captured from interactions with an individual application. The quality of recommen...

Neighbor Embedding (NE) that aims to preserve pairwise similarities between data items has been shown to yield an effective principle for data visualization. However, even the currently best NE methods such as Stochastic Neighbor Embedding (SNE) may leave large-scale patterns such as clusters hidden despite of strong signals being present in the da...

Drug combination therapy is a promising strategy to treat complex diseases such as cancer and infectious diseases. However, current knowledge of drug combination therapies, especially in cancer patients, is limited because of adverse drug effects, toxicity and cell line heterogeneity. Screening new drug combinations requires substantial efforts sin...

AI for supporting designers needs to be rethought. It should aim to cooperate, not automate, by supporting and leveraging the creativity and problem-solving of designers. The challenge for such AI is how to infer designers' goals and then help them without being needlessly disruptive. We present AI-assisted design: a framework for creating such AI,...

Generalized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst's repertoire and often used on sensitive datasets. A large body of prior works that investigate GLMs under differential privacy (DP) constraints provide only private point estimates of the regression coefficients, and are not able to qua...

Recent machine learning advances have proposed black-box estimation of unknown continuous-time system dynamics directly from data. However, earlier works are based on approximative ODE solutions or point estimates. We propose a novel Bayesian nonparametric model that uses Gaussian processes to infer posteriors of unknown ODE systems directly from d...

Active learning is usually applied to acquire labels of informative data points in supervised learning, to maximize accuracy in a sample-efficient way. However, maximizing the accuracy is not the end goal when the results are used for decision-making, for example in personalized medicine or economics. We argue that when acquiring samples sequential...