@article{21839, abstract = {Background & Aims: To develop and validate a CT-based radiomics model to assess HVPG and predict a composite endpoint of liver-related events (LRE: decompensation and liver-related death) in patients with cirrhosis. Methods: This retrospective study included 357 cirrhosis patients, who received invasive HVPG measurements, 120 liver-healthy controls (training cohort) and 85 and 100 cirrhosis patients (internal and external validation cohorts, respectively), and contrast-enhanced abdominal CTs. After volumetric segmentation of the liver and spleen on CT, Bayesian parameter optimization was used for selection of extracted features and hyperparameter tuning in random forest or elastic net models. Prediction accuracy was evaluated using Pearson correlation coefficients of predicted (’radio-HVPG’) and invasive HVPG. Discrimination between relevant HVPG cut-offs was determined by receiver operating characteristic (ROC) analysis. The predictive value of radio-HVPG and invasive-HVPG for LRE was compared using Cox regression models. Results: Radio-HVPG, predicted by an optimized random forest model based on 74 selected CT features, correlated with invasive-HVPG and detected clinically significant portal hypertension (CSPH: HVPG ≥ 10 mmHg) on the internal (Pearson r = 0.63, AUC 0.89 [95% CI: 0.81–0.96]) and external (Pearson r = 0.62, AUC 0.80 [95% CI: 0.64–0.91]) validation cohorts. Radio-HVPG predicted LRE when adjusting for MELD and albumin (adjusted HR: 1.14 [95% CI: 1.04–1.25], p = 0.005) and performed similarly to invasive-HVPG. Conclusions: Radiomic features accurately predict HVPG in patients with cirrhosis and allow risk stratification for LRE in a radiomics-clinical signature.}, author = {Sin, Celine and Watzenboeck, Martin Luther and Iofinova, Eugenia B and Balcar, Lorenz and Semmler, Georg and Scheiner, Bernhard and Lampichler, Katharina and Mandorfer, Mattias and Moga, Lucile and Rautou, Pierre‐Emmanuel and Ronot, Maxime and Menche, Jörg and Reiberger, Thomas and Scharitzer, Martina}, issn = {1478-3231}, journal = {Liver International}, keywords = {computed tomography, liver, portal hypertension, radiomics, spleen}, number = {5}, publisher = {Wiley}, title = {{Radiomics‐based assessment of portal hypertension severity and risk stratification of cirrhotic patients using routine CT scans}}, doi = {10.1111/liv.70633}, volume = {46}, year = {2026}, } @phdthesis{21854, abstract = {As neural-network-based models grow both in size and popularity, interest has grown in making the models smaller and more efficient to train. To that end, many methods have been proposed to prune models by reducing their number of nonzero parameters. Additionally, parameter-efficient fine-tuning, in which a much smaller number of parameters than the total contained in the model is updated during training, has become very popular, especially in the space of Large Language Models. At the same time, the increasingly routine deployment of machine learning in real-world applications has spurred a drive to make them more trustworthy - in the sense of, among other things, being unbiased, interpretable, and editable. In this thesis, we examine the interplay between efficiency and trustworthiness. First, we analyze the effects of model pruning on bias in computer vision models, demonstrating that increased sparsity leads to greater bias, largely as a function of increased model uncertainty in marginal cases. Based on this observation, we propose several bias mitigation techniques. Then, we demonstrate that example-specific model pruning can improve model interpretation methods while improving pruning efficiency to make example-specific model pruning feasible in real time. Then, we investigate the effectiveness of parameter-efficient and data-efficient model personalization via fine-tuning, demonstrating that it is highly feasible with very small computational and data resources. Finally, we consider efficiency in editing model knowledge using a custom synthetic data framework, demonstrating that parameter-efficient, low-rank fine-tuning frequently outperforms full-rank fine-tuning, and, additionally, that restricting which model blocks are fine-tuned frequently improves results. Together, the results in this thesis provide new insights and techniques for combining trustworthiness and efficiency during neural network inference and training. -----------------“In reference to IEEE copyrighted material which is used with permission in this thesis, the IEEE does not endorse any of [name of university or educational entity]’s products or services. Internal or personal use of this material is permitted. If interested in reprinting/republishing IEEE copyrighted material for advertising or promotional purposes or for creating new collective works for resale or redistribution, please go to http://www.ieee.org/publications_standards/publications/rights/rights_link.html to learn how to obtain a License from RightsLink. If applicable, University Microfilms and/or ProQuest Library, or the Archives of Canada may supply single copies of the dissertation.”}, author = {Iofinova, Eugenia B}, issn = {2663-337X}, pages = {237}, publisher = {Institute of Science and Technology Austria}, title = {{On the utility and effects of efficiency in artificial neural networks}}, doi = {10.15479/AT-ISTA-21854}, year = {2026}, } @misc{21857, abstract = {The availability of powerful open-source large language models (LLMs) opens exciting use cases, such as using personal data to fine-tune these models to imitate a user’s unique writing style. Two key requirements for this functionality are personalization–in the sense that the output should recognizably reflect the user’s own writing style—and privacy–users may justifiably be wary of uploading extremely personal data, such as their email archive, to a third-party service. In this paper, we demonstrate the feasibility of training and running such an assistant, which we call Panza, on commodity hardware, for the specific use case of email generation. Panza’s personalization features are based on a combination of parameter-efficient fine-tuning using a variant of the Reverse Instructions technique [1] and Retrieval-Augmented Generation (RAG) [2]. We demonstrate that this combination allows us to fine-tune an LLM to reflect a user’s writing style using limited data, while executing on extremely limited resources, e.g. on a free Google Colab instance. Our key methodological contribution is the first detailed study of evaluation metrics for this task, and of how different choices of system components–the use of RAG and of different fine-tuning approaches–impact the system’s performance. Additionally, we demonstrate that very little data - under 100 email samples - are sufficient to create models that convincingly imitate humans, showcasing a previously unknown attack vector in language models. We are releasing the full Panza code as well as three new email datasets licensed for research use.}, author = {Nicolicioiu, Armand and Iofinova, Eugenia B and Jovanovic, Andrej and Kurtic, Eldar and Nikdan, Mahdi and Panferov, Andrei and Markov, Ilia and Shavit, Nir and Alistarh, Dan-Adrian}, booktitle = {Third Conference on Parsimony and Learning (Proceedings Track)}, keywords = {LLMs, PEFT, LoRA, personalization, efficient ML}, location = {Tübíngen, Germany}, publisher = {OpenReview}, title = {{Panza: Investigating the feasibility of fully-local personalized text generation}}, year = {2026}, } @unpublished{21859, abstract = {As artificial neural networks, and specifically large language models, have improved rapidly in capabilities and quality, they have increasingly been deployed in real-world applications, from customer service to Google search, despite the fact that they frequently make factually incorrect or undesirable statements. This trend has inspired practical and academic interest in model editing, that is, in adjusting the weights of the model to modify its likely outputs for queries relating to a specific fact or set of facts. This may be done either to amend a fact or set of facts, for instance, to fix a frequent error in the training data, or to suppress a fact or set of facts entirely, for instance, in case of dangerous knowledge. Multiple methods have been proposed to do such edits. However, at the same time, it has been shown that such model editing can be brittle and incomplete. Moreover the effectiveness of any model editing method necessarily depends on the data on which the model is trained, and, therefore, a good understanding of the interaction of the training data distribution and the way it is stored in the network is necessary and helpful to reliably perform model editing. However, working with large language models trained on real-world data does not allow us to understand this relationship or fully measure the effects of model editing. We therefore propose Behemoth, a fully synthetic data generation framework. To demonstrate the practical insights from the framework, we explore model editing in the context of simple tabular data, demonstrating surprising findings that, in some cases, echo real-world results, for instance, that in some cases restricting the update rank results in a more effective update.}, author = {Iofinova, Eugenia B and Alistarh, Dan-Adrian}, booktitle = {arXiv}, title = {{Behemoth: Benchmarking unlearning in LLMs using fully synthetic data}}, doi = {10.48550/arXiv.2601.23153}, year = {2026}, } @unpublished{21858, abstract = {The recent surge in high-quality open-source Generative AI text models (colloquially: LLMs), as well as efficient finetuning techniques, have opened the possibility of creating high-quality personalized models that generate text attuned to a specific individual’s needs and are capable of credibly imitating their writing style by refining an open-source model with that person’s own data. The technology to create such models is accessible to private individuals, and training and running such models can be done cheaply on consumer-grade hardware. While these advancements are a huge gain for usability and privacy, this position paper argues that the practical feasibility of impersonating specific individuals also introduces novel safety risks. For instance, this technology enables the creation of phishing emails or fraudulent social media accounts, based on small amounts of publicly available text, or by the individuals themselves to escape AI text detection. We further argue that these risks are complementary to—and distinct from—the much-discussed risks of other impersonation attacks such as image, voice, or video deepfakes, and are not adequately addressed by the larger research community, or the current generation of open- and closed-source models.}, author = {Iofinova, Eugenia B and Jovanovic, Andrej and Alistarh, Dan-Adrian}, booktitle = {arXiv}, title = {{Position: It's time to act on the risk of efficient personalized text generation}}, doi = {10.48550/arXiv.2502.06560}, year = {2025}, } @inproceedings{18121, abstract = {It is known that sparsity can improve interpretability for deep neural networks. However, existing methods in the area either require networks that are pre-trained with sparsity constraints, or impose sparsity after the fact, altering the network’s general behavior. In this paper, we demonstrate, for the first time, that sparsity can instead be incorporated into the interpretation process itself, as a sample-specific preprocessing step. Unlike previous work, this approach, which we call SPADE, does not place constraints on the trained model and does not affect its behavior during inference on the sample. Given a trained model and a target sample, SPADE uses sample-targeted pruning to provide a "trace" of the network’s execution on the sample, reducing the network to the most important connections prior to computing an interpretation. We demonstrate that preprocessing with SPADE significantly increases the accuracy of image saliency maps across several interpretability methods. Additionally, SPADE improves the usefulness of neuron visualizations, aiding humans in reasoning about network behavior. Our code is available at https://github.com/IST-DASLab/SPADE.}, author = {Moakhar, Arshia Soltani and Iofinova, Eugenia B and Frantar, Elias and Alistarh, Dan-Adrian}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, issn = {2640-3498}, location = {Vienna, Austria}, pages = {45955--45987}, publisher = {ML Research Press}, title = {{SPADE: Sparsity-guided debugging for deep neural networks}}, volume = {235}, year = {2024}, } @inproceedings{14460, abstract = {We provide an efficient implementation of the backpropagation algorithm, specialized to the case where the weights of the neural network being trained are sparse. Our algorithm is general, as it applies to arbitrary (unstructured) sparsity and common layer types (e.g., convolutional or linear). We provide a fast vectorized implementation on commodity CPUs, and show that it can yield speedups in end-to-end runtime experiments, both in transfer learning using already-sparsified networks, and in training sparse networks from scratch. Thus, our results provide the first support for sparse training on commodity hardware.}, author = {Nikdan, Mahdi and Pegolotti, Tommaso and Iofinova, Eugenia B and Kurtic, Eldar and Alistarh, Dan-Adrian}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, issn = {2640-3498}, location = {Honolulu, Hawaii, HI, United States}, pages = {26215--26227}, publisher = {ML Research Press}, title = {{SparseProp: Efficient sparse backpropagation for faster training of neural networks at the edge}}, volume = {202}, year = {2023}, } @inproceedings{14771, abstract = {Pruning—that is, setting a significant subset of the parameters of a neural network to zero—is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may induce or exacerbate bias in the output of the compressed model. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood. In this work, we systematically investigate and characterize this phenomenon in Convolutional Neural Networks for computer vision. First, we show that it is in fact possible to obtain highly-sparse models, e.g. with less than 10% remaining weights, which do not decrease in accuracy nor substantially increase in bias when compared to dense models. At the same time, we also find that, at higher sparsities, pruned models exhibit higher uncertainty in their outputs, as well as increased correlations, which we directly link to increased bias. We propose easy-to-use criteria which, based only on the uncompressed model, establish whether bias will increase with pruning, and identify the samples most susceptible to biased predictions post-compression. Our code can be found at https://github.com/IST-DASLab/pruned-vision-model-bias.}, author = {Iofinova, Eugenia B and Peste, Elena-Alexandra and Alistarh, Dan-Adrian}, booktitle = {2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {Vancouver, BC, Canada}, pages = {24364--24373}, publisher = {IEEE}, title = {{Bias in pruned vision models: In-depth analysis and countermeasures}}, doi = {10.1109/cvpr52729.2023.02334}, year = {2023}, } @inproceedings{12299, abstract = {Transfer learning is a classic paradigm by which models pretrained on large “upstream” datasets are adapted to yield good results on “downstream” specialized datasets. Generally, more accurate models on the “upstream” dataset tend to provide better transfer accuracy “downstream”. In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned-that is, compressed by sparsifiying their connections. We consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, regrowth, lottery-ticket, and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods. The code is available at: https://github.com/IST-DASLab/sparse-imagenet-transfer.}, author = {Iofinova, Eugenia B and Peste, Elena-Alexandra and Kurtz, Mark and Alistarh, Dan-Adrian}, booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {New Orleans, LA, United States}, pages = {12256--12266}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{How well do sparse ImageNet models transfer?}}, doi = {10.1109/cvpr52688.2022.01195}, year = {2022}, } @article{12495, abstract = {Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a fast-growing area of machine learning with far-reaching societal impact. However, existing fair learning methods are vulnerable to accidental or malicious artifacts in the training data, which can cause them to unknowingly produce unfair classifiers. In this work we address the problem of fair learning from unreliable training data in the robust multisource setting, where the available training data comes from multiple sources, a fraction of which might not be representative of the true data distribution. We introduce FLEA, a filtering-based algorithm that identifies and suppresses those data sources that would have a negative impact on fairness or accuracy if they were used for training. As such, FLEA is not a replacement of prior fairness-aware learning methods but rather an augmentation that makes any of them robust against unreliable training data. We show the effectiveness of our approach by a diverse range of experiments on multiple datasets. Additionally, we prove formally that –given enough data– FLEA protects the learner against corruptions as long as the fraction of affected data sources is less than half. Our source code and documentation are available at https://github.com/ISTAustria-CVML/FLEA.}, author = {Iofinova, Eugenia B and Konstantinov, Nikola H and Lampert, Christoph}, issn = {2835-8856}, journal = {Transactions on Machine Learning Research}, publisher = {ML Research Press}, title = {{FLEA: Provably robust fair multisource learning from unreliable training data}}, year = {2022}, } @inproceedings{11458, abstract = {The increasing computational requirements of deep neural networks (DNNs) have led to significant interest in obtaining DNN models that are sparse, yet accurate. Recent work has investigated the even harder case of sparse training, where the DNN weights are, for as much as possible, already sparse to reduce computational costs during training. Existing sparse training methods are often empirical and can have lower accuracy relative to the dense baseline. In this paper, we present a general approach called Alternating Compressed/DeCompressed (AC/DC) training of DNNs, demonstrate convergence for a variant of the algorithm, and show that AC/DC outperforms existing sparse training methods in accuracy at similar computational budgets; at high sparsity levels, AC/DC even outperforms existing methods that rely on accurate pre-trained dense models. An important property of AC/DC is that it allows co-training of dense and sparse models, yielding accurate sparse–dense model pairs at the end of the training process. This is useful in practice, where compressed variants may be desirable for deployment in resource-constrained settings without re-doing the entire training flow, and also provides us with insights into the accuracy gap between dense and compressed models. The code is available at: https://github.com/IST-DASLab/ACDC.}, author = {Peste, Elena-Alexandra and Iofinova, Eugenia B and Vladu, Adrian and Alistarh, Dan-Adrian}, booktitle = {35th Conference on Neural Information Processing Systems}, isbn = {9781713845393}, issn = {1049-5258}, location = {Virtual, Online}, pages = {8557--8570}, publisher = {Neural Information Processing Systems Foundation}, title = {{AC/DC: Alternating Compressed/DeCompressed training of deep neural networks}}, volume = {34}, year = {2021}, }