TY - CONF AB - We present a technique to optimize the reflectivity of a surface while preserving its overall shape. The naïve optimization of the mesh vertices using the gradients of reflectivity simulations results in undesirable distortion. In contrast, our robust formulation optimizes the surface normal as an independent variable that bridges the reflectivity term with differential rendering, and the regularization term with as-rigid-as-possible elastic energy. We further adaptively subdivide the input mesh to improve the convergence. Consequently, our method can minimize the retroreflectivity of a wide range of input shapes, resulting in sharply creased shapes ubiquitous among stealth aircraft and Sci-Fi vehicles. Furthermore, by changing the reward for the direction of the outgoing light directions, our method can be applied to other reflectivity design tasks, such as the optimization of architectural walls to concentrate light in a specific region. We have tested the proposed method using light-transport simulations and real-world 3D-printed objects. AU - Tojo, Kenji AU - Shamir, Ariel AU - Bickel, Bernd AU - Umetani, Nobuyuki ID - 14241 SN - 9798400701597 T2 - SIGGRAPH 2023 Conference Proceedings TI - Stealth shaper: Reflectivity optimization as surface stylization ER - TY - JOUR AB - Presynaptic inputs determine the pattern of activation of postsynaptic neurons in a neural circuit. Molecular and genetic pathways that regulate the selective formation of subsets of presynaptic inputs are largely unknown, despite significant understanding of the general process of synaptogenesis. In this study, we have begun to identify such factors using the spinal monosynaptic stretch reflex circuit as a model system. In this neuronal circuit, Ia proprioceptive afferents establish monosynaptic connections with spinal motor neurons that project to the same muscle (termed homonymous connections) or muscles with related or synergistic function. However, monosynaptic connections are not formed with motor neurons innervating muscles with antagonistic functions. The ETS transcription factor ER81 (also known as ETV1) is expressed by all proprioceptive afferents, but only a small set of motor neuron pools in the lumbar spinal cord of the mouse. Here we use conditional mouse genetic techniques to eliminate Er81 expression selectively from motor neurons. We find that ablation of Er81 in motor neurons reduces synaptic inputs from proprioceptive afferents conveying information from homonymous and synergistic muscles, with no change observed in the connectivity pattern from antagonistic proprioceptive afferents. In summary, these findings suggest a role for ER81 in defined motor neuron pools to control the assembly of specific presynaptic inputs and thereby influence the profile of activation of these motor neurons. AU - Ladle, David R. AU - Hippenmeyer, Simon ID - 12562 IS - 3 JF - Journal of Neurophysiology KW - Physiology KW - General Neuroscience SN - 0022-3077 TI - Loss of ETV1/ER81 in motor neurons leads to reduced monosynaptic inputs from proprioceptive sensory neurons VL - 129 ER - TY - CONF AB - Machine-learned systems are in widespread use for making decisions about humans, and it is important that they are fair, i.e., not biased against individuals based on sensitive attributes. We present runtime verification of algorithmic fairness for systems whose models are unknown, but are assumed to have a Markov chain structure. We introduce a specification language that can model many common algorithmic fairness properties, such as demographic parity, equal opportunity, and social burden. We build monitors that observe a long sequence of events as generated by a given system, and output, after each observation, a quantitative estimate of how fair or biased the system was on that run until that point in time. The estimate is proven to be correct modulo a variable error bound and a given confidence level, where the error bound gets tighter as the observed sequence gets longer. Our monitors are of two types, and use, respectively, frequentist and Bayesian statistical inference techniques. While the frequentist monitors compute estimates that are objectively correct with respect to the ground truth, the Bayesian monitors compute estimates that are correct subject to a given prior belief about the system’s model. Using a prototype implementation, we show how we can monitor if a bank is fair in giving loans to applicants from different social backgrounds, and if a college is fair in admitting students while maintaining a reasonable financial burden on the society. Although they exhibit different theoretical complexities in certain cases, in our experiments, both frequentist and Bayesian monitors took less than a millisecond to update their verdicts after each observation. AU - Henzinger, Thomas A AU - Karimi, Mahyar AU - Kueffner, Konstantin AU - Mallik, Kaushik ID - 13310 SN - 0302-9743 T2 - Computer Aided Verification TI - Monitoring algorithmic fairness VL - 13965 ER - TY - JOUR AB - Background: This study seeks to evaluate the impact of breast cancer (BRCA) gene status on tumor dissemination pattern, surgical outcome and survival in a multicenter cohort of paired primary ovarian cancer (pOC) and recurrent ovarian cancer (rOC). Patients and Methods: Medical records and follow-up data from 190 patients were gathered retrospectively. All patients had surgery at pOC and at least one further rOC surgery at four European high-volume centers. Patients were divided into one cohort with confirmed mutation for BRCA1 and/or BRCA2 (BRCAmut) and a second cohort with BRCA wild type or unknown (BRCAwt). Patterns of tumor presentation, surgical outcome and survival data were analyzed between the two groups. Results: Patients with BRCAmut disease were on average 4 years younger and had significantly more tumor involvement upon diagnosis. Patients with BRCAmut disease showed higher debulking rates at all stages. Multivariate analysis showed that only patient age had significant predictive value for complete tumor resection in pOC. At rOC, however, only BRCAmut status significantly correlated with optimal debulking. Patients with BRCAmut disease showed significantly prolonged overall survival (OS) by 24.3 months. Progression-free survival (PFS) was prolonged in the BRCAmut group at all stages as well, reaching statistical significance during recurrence. Conclusions: Patients with BRCAmut disease showed a more aggressive course of disease with earlier onset and more extensive tumor dissemination at pOC. However, surgical outcome and OS were significantly better in patients with BRCAmut disease compared with patients with BRCAwt disease. We therefore propose to consider BRCAmut status in regard to patient selection for cytoreductive surgery, especially in rOC. AU - Glajzer, Jacek AU - Castillo-Tong, Dan Cacsire AU - Richter, Rolf AU - Vergote, Ignace AU - Kulbe, Hagen AU - Vanderstichele, Adriaan AU - Ruscito, Ilary AU - Trillsch, Fabian AU - Mustea, Alexander AU - Kreuzinger, Caroline AU - Gourley, Charlie AU - Gabra, Hani AU - Taube, Eliane T. AU - Dorigo, Oliver AU - Horst, David AU - Keunecke, Carlotta AU - Baum, Joanna AU - Angelotti, Timothy AU - Sehouli, Jalid AU - Braicu, Elena Ioana ID - 12205 JF - Annals of Surgical Oncology KW - Oncology KW - Surgery SN - 1068-9265 TI - Impact of BRCA mutation status on tumor dissemination pattern, surgical outcome and patient survival in primary and recurrent high-grade serous ovarian cancer: A multicenter retrospective study by the Ovarian Cancer Therapy-Innovative Models Prolong Survival (OCTIPS) consortium VL - 30 ER - TY - JOUR AU - Glajzer, Jacek AU - Castillo-Tong, Dan Cacsire AU - Richter, Rolf AU - Vergote, Ignace AU - Kulbe, Hagen AU - Vanderstichele, Adriaan AU - Ruscito, Ilary AU - Trillsch, Fabian AU - Mustea, Alexander AU - Kreuzinger, Caroline AU - Gourley, Charlie AU - Gabra, Hani AU - Taube, Eliane T. AU - Dorigo, Oliver AU - Horst, David AU - Keunecke, Carlotta AU - Baum, Joanna AU - Angelotti, Timothy AU - Sehouli, Jalid AU - Braicu, Elena Ioana ID - 12115 JF - Annals of Surgical Oncology KW - Oncology KW - Surgery SN - 1068-9265 TI - ASO Visual Abstract: Impact of BRCA mutation status on tumor dissemination pattern, surgical outcome, and patient survival in primary and recurrent high-grade serous ovarian cancer (HGSOC). A multicenter, retrospective study of the ovarian cancer therapy—innovative models prolong survival (OCTIPS) consortium VL - 30 ER - TY - JOUR AB - Junctions between the endoplasmic reticulum (ER) and the plasma membrane (PM) are specialized membrane contacts ubiquitous in eukaryotic cells. Concentration of intracellular signaling machinery near ER-PM junctions allows these domains to serve critical roles in lipid and Ca2+ signaling and homeostasis. Subcellular compartmentalization of protein kinase A (PKA) signaling also regulates essential cellular functions, however, no specific association between PKA and ER-PM junctional domains is known. Here, we show that in brain neurons type I PKA is directed to Kv2.1 channel-dependent ER-PM junctional domains via SPHKAP, a type I PKA-specific anchoring protein. SPHKAP association with type I PKA regulatory subunit RI and ER-resident VAP proteins results in the concentration of type I PKA between stacked ER cisternae associated with ER-PM junctions. This ER-associated PKA signalosome enables reciprocal regulation between PKA and Ca2+ signaling machinery to support Ca2+ influx and excitation-transcription coupling. These data reveal that neuronal ER-PM junctions support a receptor-independent form of PKA signaling driven by membrane depolarization and intracellular Ca2+, allowing conversion of information encoded in electrical signals into biochemical changes universally recognized throughout the cell. AU - Vierra, Nicholas C. AU - Ribeiro-Silva, Luisa AU - Kirmiz, Michael AU - Van Der List, Deborah AU - Bhandari, Pradeep AU - Mack, Olivia A. AU - Carroll, James AU - Le Monnier, Elodie AU - Aicher, Sue A. AU - Shigemoto, Ryuichi AU - Trimmer, James S. ID - 14253 JF - Nature Communications TI - Neuronal ER-plasma membrane junctions couple excitation to Ca2+-activated PKA signaling VL - 14 ER - TY - CONF AB - We provide a learning-based technique for guessing a winning strategy in a parity game originating from an LTL synthesis problem. A cheaply obtained guess can be useful in several applications. Not only can the guessed strategy be applied as best-effort in cases where the game’s huge size prohibits rigorous approaches, but it can also increase the scalability of rigorous LTL synthesis in several ways. Firstly, checking whether a guessed strategy is winning is easier than constructing one. Secondly, even if the guess is wrong in some places, it can be fixed by strategy iteration faster than constructing one from scratch. Thirdly, the guess can be used in on-the-fly approaches to prioritize exploration in the most fruitful directions. In contrast to previous works, we (i) reflect the highly structured logical information in game’s states, the so-called semantic labelling, coming from the recent LTL-to-automata translations, and (ii) learn to reflect it properly by learning from previously solved games, bringing the solving process closer to human-like reasoning. AU - Kretinsky, Jan AU - Meggendorfer, Tobias AU - Prokop, Maximilian AU - Rieder, Sabine ID - 14259 SN - 0302-9743 T2 - 35th International Conference on Computer Aided Verification TI - Guessing winning policies in LTL synthesis by semantic learning VL - 13964 ER - TY - CONF AB - Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to inference. With no labels available this requires unsupervised objectives to adapt the model on the observed test data. In this paper, we propose Test-Time SelfTraining (TeST): a technique that takes as input a model trained on some source data and a novel data distribution at test time, and learns invariant and robust representations using a student-teacher framework. We find that models adapted using TeST significantly improve over baseline testtime adaptation algorithms. TeST achieves competitive performance to modern domain adaptation algorithms [4, 43], while having access to 5-10x less data at time of adaption. We thoroughly evaluate a variety of baselines on two tasks: object detection and image segmentation and find that models adapted with TeST. We find that TeST sets the new stateof-the art for test-time domain adaptation algorithms. AU - Sinha, Samarth AU - Gehler, Peter AU - Locatello, Francesco AU - Schiele, Bernt ID - 14105 SN - 9781665493475 T2 - 2023 IEEE/CVF Winter Conference on Applications of Computer Vision TI - TeST: Test-time Self-Training under distribution shift ER - TY - JOUR AB - Context. Space asteroseismology is revolutionizing our knowledge of the internal structure and dynamics of stars. A breakthrough is ongoing with the recent discoveries of signatures of strong magnetic fields in the core of red giant stars. The key signature for such a detection is the asymmetry these fields induce in the frequency splittings of observed dipolar mixed gravito-acoustic modes. Aims. We investigate the ability of the observed asymmetries of the frequency splittings of dipolar mixed modes to constrain the geometrical properties of deep magnetic fields. Methods. We used the powerful analytical Racah-Wigner algebra used in quantum mechanics to characterize the geometrical couplings of dipolar mixed oscillation modes with various realistically plausible topologies of fossil magnetic fields. We also computed the induced perturbation of their frequencies. Results. First, in the case of an oblique magnetic dipole, we provide the exact analytical expression of the asymmetry as a function of the angle between the rotation and magnetic axes. Its value provides a direct measure of this angle. Second, considering a combination of axisymmetric dipolar and quadrupolar fields, we show how the asymmetry is blind to the unraveling of the relative strength and sign of each component. Finally, in the case of a given multipole, we show that a negative asymmetry is a signature of non-axisymmetric topologies. Conclusions. Asymmetries of dipolar mixed modes provide a key bit of information on the geometrical topology of deep fossil magnetic fields, but this is insufficient on its own. Asteroseismic constraints should therefore be combined with spectropolarimetric observations and numerical simulations, which aim to predict the more probable stable large-scale geometries. AU - Mathis, S. AU - Bugnet, Lisa Annabelle ID - 14256 JF - Astronomy and Astrophysics SN - 0004-6361 TI - Asymmetries of frequency splittings of dipolar mixed modes: A window on the topology of deep magnetic fields VL - 676 ER - TY - JOUR AB - In this work, a generalized, adapted Numerov implementation capable of determining band structures of periodic quantum systems is outlined. Based on the input potential, the presented approach numerically solves the Schrödinger equation in position space at each momentum space point. Thus, in addition to the band structure, the method inherently provides information about the state functions and probability densities in position space at each momentum space point considered. The generalized, adapted Numerov framework provided reliable estimates for a variety of increasingly complex test suites in one, two, and three dimensions. The accuracy of the proposed methodology was benchmarked against results obtained for the analytically solvable Kronig-Penney model. Furthermore, the presented numerical solver was applied to a model potential representing a 2D optical lattice being a challenging application relevant, for example, in the field of quantum computing. AU - Gamper, Jakob AU - Kluibenschedl, Florian AU - Weiss, Alexander K.H. AU - Hofer, Thomas S. ID - 14261 IS - 33 JF - Journal of Physical Chemistry Letters TI - Accessing position space wave functions in band structure calculations of periodic systems - a generalized, adapted numerov implementation for one-, two-, and three-dimensional quantum problems VL - 14 ER - TY - CONF AB - This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining (nearly) zero-training error under the lazy training regime. For this purpose, we unify three interrelated concepts of overparameterization, benign overfitting, and the Lipschitz constant of DNNs. Our results indicate that interpolating with smoother functions leads to better generalization. Furthermore, we investigate the special case where interpolating smooth ground-truth functions is performed by DNNs under the Neural Tangent Kernel (NTK) regime for generalization. Our result demonstrates that the generalization error converges to a constant order that only depends on label noise and initialization noise, which theoretically verifies benign overfitting. Our analysis provides a tight lower bound on the normalized margin under non-smooth activation functions, as well as the minimum eigenvalue of NTK under high-dimensional settings, which has its own interest in learning theory. AU - Zhu, Zhenyu AU - Liu, Fanghui AU - Chrysos, Grigorios G AU - Locatello, Francesco AU - Cevher, Volkan ID - 14208 T2 - Proceedings of the 40th International Conference on Machine Learning TI - Benign overfitting in deep neural networks under lazy training VL - 202 ER - TY - GEN AB - Diffusion models excel at generating photorealistic images from text-queries. Naturally, many approaches have been proposed to use these generative abilities to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large noisily supervised, but nonetheless, annotated datasets. It is an open question whether the generalization capabilities of diffusion models beyond using the additional data of the pre-training process for augmentation lead to improved downstream performance. We perform a systematic evaluation of existing methods to generate images from diffusion models and study new extensions to assess their benefit for data augmentation. While we find that personalizing diffusion models towards the target data outperforms simpler prompting strategies, we also show that using the training data of the diffusion model alone, via a simple nearest neighbor retrieval procedure, leads to even stronger downstream performance. Overall, our study probes the limitations of diffusion models for data augmentation but also highlights its potential in generating new training data to improve performance on simple downstream vision tasks. AU - Burg, Max F. AU - Wenzel, Florian AU - Zietlow, Dominik AU - Horn, Max AU - Makansi, Osama AU - Locatello, Francesco AU - Russell, Chris ID - 14209 T2 - arXiv TI - A data augmentation perspective on diffusion models and retrieval ER - TY - CONF AB - Causal discovery methods are intrinsically constrained by the set of assumptions needed to ensure structure identifiability. Moreover additional restrictions are often imposed in order to simplify the inference task: this is the case for the Gaussian noise assumption on additive non-linear models, which is common to many causal discovery approaches. In this paper we show the shortcomings of inference under this hypothesis, analyzing the risk of edge inversion under violation of Gaussianity of the noise terms. Then, we propose a novel method for inferring the topological ordering of the variables in the causal graph, from data generated according to an additive non-linear model with a generic noise distribution. This leads to NoGAM (Not only Gaussian Additive noise Models), a causal discovery algorithm with a minimal set of assumptions and state of the art performance, experimentally benchmarked on synthetic data. AU - Montagna, Francesco AU - Noceti, Nicoletta AU - Rosasco, Lorenzo AU - Zhang, Kun AU - Locatello, Francesco ID - 14211 T2 - 2nd Conference on Causal Learning and Reasoning TI - Causal discovery with score matching on additive models with arbitrary noise ER - TY - CONF AB - This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational non-linear additive Gaussian noise models. Leveraging scalable machine learning approaches to approximate the score function ∇logp(X), we extend the work of Rolland et al. (2022) that only recovers the topological order from the score and requires an expensive pruning step removing spurious edges among those admitted by the ordering. Our analysis leads to DAS (acronym for Discovery At Scale), a practical algorithm that reduces the complexity of the pruning by a factor proportional to the graph size. In practice, DAS achieves competitive accuracy with current state-of-the-art while being over an order of magnitude faster. Overall, our approach enables principled and scalable causal discovery, significantly lowering the compute bar. AU - Montagna, Francesco AU - Noceti, Nicoletta AU - Rosasco, Lorenzo AU - Zhang, Kun AU - Locatello, Francesco ID - 14212 T2 - 2nd Conference on Causal Learning and Reasoning TI - Scalable causal discovery with score matching ER - TY - CONF AB - Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In this paper, we present Causal Triplet, a causal representation learning benchmark featuring not only visually more complex scenes, but also two crucial desiderata commonly overlooked in previous works: (i) an actionable counterfactual setting, where only certain object-level variables allow for counterfactual observations whereas others do not; (ii) an interventional downstream task with an emphasis on out-of-distribution robustness from the independent causal mechanisms principle. Through extensive experiments, we find that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts. However, recent causal representation learning methods still struggle to identify such latent structures, indicating substantial challenges and opportunities for future work. AU - Liu, Yuejiang AU - Alahi, Alexandre AU - Russell, Chris AU - Horn, Max AU - Zietlow, Dominik AU - Schölkopf, Bernhard AU - Locatello, Francesco ID - 14214 T2 - 2nd Conference on Causal Learning and Reasoning TI - Causal triplet: An open challenge for intervention-centric causal representation learning ER - TY - CONF AB - Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. Ideally, the distribution of the data points in the latent space should depend only on the task, the data, the loss, and other architecture-specific constraints. However, factors such as the random weights initialization, training hyperparameters, or other sources of randomness in the training phase may induce incoherent latent spaces that hinder any form of reuse. Nevertheless, we empirically observe that, under the same data and modeling choices, the angles between the encodings within distinct latent spaces do not change. In this work, we propose the latent similarity between each sample and a fixed set of anchors as an alternative data representation, demonstrating that it can enforce the desired invariances without any additional training. We show how neural architectures can leverage these relative representations to guarantee, in practice, invariance to latent isometries and rescalings, effectively enabling latent space communication: from zero-shot model stitching to latent space comparison between diverse settings. We extensively validate the generalization capability of our approach on different datasets, spanning various modalities (images, text, graphs), tasks (e.g., classification, reconstruction) and architectures (e.g., CNNs, GCNs, transformers). AU - Moschella, Luca AU - Maiorca, Valentino AU - Fumero, Marco AU - Norelli, Antonio AU - Locatello, Francesco AU - Rodolà, Emanuele ID - 14217 T2 - The 11th International Conference on Learning Representations TI - Relative representations enable zero-shot latent space communication ER - TY - CONF AB - Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling. We decompose this problem into three easier subtasks, and provide candidate solutions for each of them. Inspired by the Common Fate Principle of Gestalt Psychology, we first extract (noisy) masks of moving objects via unsupervised motion segmentation. Second, generative models are trained on the masks of the background and the moving objects, respectively. Third, background and foreground models are combined in a conditional "dead leaves" scene model to sample novel scene configurations where occlusions and depth layering arise naturally. To evaluate the individual stages, we introduce the Fishbowl dataset positioned between complex real-world scenes and common object-centric benchmarks of simplistic objects. We show that our approach allows learning generative models that generalize beyond the occlusions present in the input videos, and represent scenes in a modular fashion that allows sampling plausible scenes outside the training distribution by permitting, for instance, object numbers or densities not observed in the training set. AU - Tangemann, Matthias AU - Schneider, Steffen AU - Kügelgen, Julius von AU - Locatello, Francesco AU - Gehler, Peter AU - Brox, Thomas AU - Kümmerer, Matthias AU - Bethge, Matthias AU - Schölkopf, Bernhard ID - 14222 T2 - 2nd Conference on Causal Learning and Reasoning TI - Unsupervised object learning via common fate ER - TY - CONF AB - Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing image-based object-centric learning models on simulated data and is the first unsupervised object-centric model that scales to real-world datasets such as COCO and PASCAL VOC. DINOSAUR is conceptually simple and shows competitive performance compared to more involved pipelines from the computer vision literature. AU - Seitzer, Maximilian AU - Horn, Max AU - Zadaianchuk, Andrii AU - Zietlow, Dominik AU - Xiao, Tianjun AU - Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel AU - He, Tong AU - Zhang, Zheng AU - Schölkopf, Bernhard AU - Brox, Thomas AU - Locatello, Francesco ID - 14218 T2 - The 11th International Conference on Learning Representations TI - Bridging the gap to real-world object-centric learning ER - TY - CONF AB - In this paper, we show that recent advances in self-supervised feature learning enable unsupervised object discovery and semantic segmentation with a performance that matches the state of the field on supervised semantic segmentation 10 years ago. We propose a methodology based on unsupervised saliency masks and self-supervised feature clustering to kickstart object discovery followed by training a semantic segmentation network on pseudo-labels to bootstrap the system on images with multiple objects. We present results on PASCAL VOC that go far beyond the current state of the art (50.0 mIoU), and we report for the first time results on MS COCO for the whole set of 81 classes: our method discovers 34 categories with more than $20\%$ IoU, while obtaining an average IoU of 19.6 for all 81 categories. AU - Zadaianchuk, Andrii AU - Kleindessner, Matthaeus AU - Zhu, Yi AU - Locatello, Francesco AU - Brox, Thomas ID - 14219 T2 - The 11th International Conference on Learning Representations TI - Unsupervised semantic segmentation with self-supervised object-centric representations ER - TY - GEN AB - As causal ground truth is incredibly rare, causal discovery algorithms are commonly only evaluated on simulated data. This is concerning, given that simulations reflect common preconceptions about generating processes regarding noise distributions, model classes, and more. In this work, we propose a novel method for falsifying the output of a causal discovery algorithm in the absence of ground truth. Our key insight is that while statistical learning seeks stability across subsets of data points, causal learning should seek stability across subsets of variables. Motivated by this insight, our method relies on a notion of compatibility between causal graphs learned on different subsets of variables. We prove that detecting incompatibilities can falsify wrongly inferred causal relations due to violation of assumptions or errors from finite sample effects. Although passing such compatibility tests is only a necessary criterion for good performance, we argue that it provides strong evidence for the causal models whenever compatibility entails strong implications for the joint distribution. We also demonstrate experimentally that detection of incompatibilities can aid in causal model selection. AU - Faller, Philipp M. AU - Vankadara, Leena Chennuru AU - Mastakouri, Atalanti A. AU - Locatello, Francesco AU - Janzing, Dominik ID - 14333 T2 - arXiv TI - Self-compatibility: Evaluating causal discovery without ground truth ER -