LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 72

Search options

  1. Article ; Online: Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection.

    Zhang, Lily H / Ranganath, Rajesh

    Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence

    2024  Volume 37, Issue 12, Page(s) 15305–15312

    Abstract: Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (ood) detection of image inputs. However, these methods struggle to detect ood inputs that share nuisance ... ...

    Abstract Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (ood) detection of image inputs. However, these methods struggle to detect ood inputs that share nuisance values (e.g. background) with in-distribution inputs. The detection of shared-nuisance out-of-distribution (sn-ood) inputs is particularly relevant in real-world applications, as anomalies and in-distribution inputs tend to be captured in the same settings during deployment. In this work, we provide a possible explanation for sn-ood detection failures and propose
    Language English
    Publishing date 2024-02-23
    Publishing country United States
    Document type Journal Article
    ISSN 2374-3468
    ISSN (online) 2374-3468
    DOI 10.1609/aaai.v37i12.26785
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics.

    Murali, Nihal / Puli, Aahlad / Yu, Ke / Ranganath, Rajesh / Batmanghelich, Kayhan

    Transactions on machine learning research

    2024  Volume 2023

    Abstract: Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and poses problems when deploying them in safety-critical ... ...

    Abstract Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and poses problems when deploying them in safety-critical applications. This paper aims to better understand the effects of spurious features through the lens of the learning dynamics of the internal neurons during the training process. We make the following observations: (1) While previous works highlight the harmful effects of spurious features on the generalization ability of DNNs, we emphasize that not all spurious features are harmful. Spurious features can be "
    Language English
    Publishing date 2024-04-09
    Publishing country United States
    Document type Journal Article
    ISSN 2835-8856
    ISSN (online) 2835-8856
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Article ; Online: Survival Mixture Density Networks.

    Han, Xintian / Goldstein, Mark / Ranganath, Rajesh

    Proceedings of machine learning research

    2023  Volume 182, Page(s) 224–248

    Abstract: Survival analysis, the art of time-to-event modeling, plays an important role in clinical treatment decisions. Recently, continuous time models built from neural ODEs have been proposed for survival analysis. However, the training of neural ODEs is slow ... ...

    Abstract Survival analysis, the art of time-to-event modeling, plays an important role in clinical treatment decisions. Recently, continuous time models built from neural ODEs have been proposed for survival analysis. However, the training of neural ODEs is slow due to the high computational complexity of neural ODE solvers. Here, we propose an efficient alternative for flexible continuous time models, called Survival Mixture Density Networks (Survival MDNs). Survival MDN applies an invertible positive function to the output of Mixture Density Networks (MDNs). While MDNs produce flexible real-valued distributions, the invertible positive function maps the model into the time-domain while preserving a tractable density. Using four datasets, we show that Survival MDN performs better than, or similarly to continuous and discrete time baselines on concordance, integrated Brier score and integrated binomial log-likelihood. Meanwhile, Survival MDNs are also faster than ODE-based models and circumvent binning issues in discrete models.
    Language English
    Publishing date 2023-09-08
    Publishing country United States
    Document type Journal Article
    ISSN 2640-3498
    ISSN (online) 2640-3498
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: DIET: Conditional independence testing with marginal dependence measures of residual information.

    Sudarshan, Mukund / Puli, Aahlad / Tansey, Wesley / Ranganath, Rajesh

    Proceedings of machine learning research

    2023  Volume 206, Page(s) 10343–10367

    Abstract: Conditional randomization tests (CRTs) assess whether a ... ...

    Abstract Conditional randomization tests (CRTs) assess whether a variable
    Language English
    Publishing date 2023-08-22
    Publishing country United States
    Document type Journal Article
    ISSN 2640-3498
    ISSN (online) 2640-3498
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Book ; Online: Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection

    Zhang, Lily H. / Ranganath, Rajesh

    2023  

    Abstract: Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. However, these methods struggle to detect OOD inputs that share nuisance ... ...

    Abstract Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. However, these methods struggle to detect OOD inputs that share nuisance values (e.g. background) with in-distribution inputs. The detection of shared-nuisance out-of-distribution (SN-OOD) inputs is particularly relevant in real-world applications, as anomalies and in-distribution inputs tend to be captured in the same settings during deployment. In this work, we provide a possible explanation for SN-OOD detection failures and propose nuisance-aware OOD detection to address them. Nuisance-aware OOD detection substitutes a classifier trained via empirical risk minimization and cross-entropy loss with one that 1. is trained under a distribution where the nuisance-label relationship is broken and 2. yields representations that are independent of the nuisance under this distribution, both marginally and conditioned on the label. We can train a classifier to achieve these objectives using Nuisance-Randomized Distillation (NuRD), an algorithm developed for OOD generalization under spurious correlations. Output- and feature-based nuisance-aware OOD detection perform substantially better than their original counterparts, succeeding even when detection based on domain generalization algorithms fails to improve performance.

    Comment: AAAI 2023
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
    Subject code 006
    Publishing date 2023-02-08
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Article: General Control Functions for Causal Effect Estimation from Instrumental Variables.

    Puli, Aahlad / Ranganath, Rajesh

    Advances in neural information processing systems

    2021  Volume 33, Page(s) 8440–8451

    Abstract: Causal effect estimation relies on separating the variation in the outcome into parts due to the treatment and due to the confounders. To achieve this separation, practitioners often use external sources of randomness that only influence the treatment ... ...

    Abstract Causal effect estimation relies on separating the variation in the outcome into parts due to the treatment and due to the confounders. To achieve this separation, practitioners often use external sources of randomness that only influence the treatment called instrumental variables (IVs). We study variables constructed from treatment and IV that help estimate effects, called control functions. We characterize general control functions for effect estimation in a meta-identification result. Then, we show that structural assumptions on the treatment process allow the construction of general control functions, thereby guaranteeing identification. To construct general control functions and estimate effects, we develop the general control function method (GCFN). GCFN's first stage called variational decoupling (VDE) constructs general control functions by recovering the residual variation in the treatment given the IV. Using VDE's control function, GCFN's second stage estimates effects via regression. Further, we develop semi-supervised GCFN to construct general control functions using subsets of data that have both IV and confounders observed as supervision; this needs no structural treatment process assumptions. We evaluate GCFN on low and high dimensional simulated data and on recovering the causal effect of slave export on modern community trust [30].
    Language English
    Publishing date 2021-03-25
    Publishing country United States
    Document type Journal Article
    ZDB-ID 1012320-9
    ISSN 1049-5258
    ISSN 1049-5258
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Article ; Online: Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets.

    Zhang, Lily H / Tozzo, Veronica / Higgins, John M / Ranganath, Rajesh

    Proceedings of machine learning research

    2023  Volume 162, Page(s) 26559–26574

    Abstract: Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set Transformer, can suffer from vanishing or exploding gradients when they are ...

    Abstract Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set Transformer, can suffer from vanishing or exploding gradients when they are deep. Additionally, layer norm, the normalization of choice in Set Transformer, can hurt performance by removing information useful for prediction. To address these issues, we introduce the "clean path principle" for equivariant residual connections and develop set norm (sn), a normalization tailored for sets. With these, we build Deep Sets++ and Set Transformer++, models that reach high depths with better or comparable performance than their original counterparts on a diverse suite of tasks. We additionally introduce Flow-RBC, a new single-cell dataset and real-world application of permutation invariant prediction. We open-source our data and code here: https://github.com/rajesh-lab/deep_permutation_invariant.
    Language English
    Publishing date 2023-08-17
    Publishing country United States
    Document type Journal Article
    ISSN 2640-3498
    ISSN (online) 2640-3498
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Article ; Online: Understanding Failures in Out-of-Distribution Detection with Deep Generative Models.

    Zhang, Lily H / Goldstein, Mark / Ranganath, Rajesh

    Proceedings of machine learning research

    2022  Volume 139, Page(s) 12427–12436

    Abstract: Deep generative models (dgms) seem a natural fit for detecting out-of-distribution (ood) inputs, but such models have been shown to assign higher probabilities or densities to ood images than images from the training distribution. In this work, we ... ...

    Abstract Deep generative models (dgms) seem a natural fit for detecting out-of-distribution (ood) inputs, but such models have been shown to assign higher probabilities or densities to ood images than images from the training distribution. In this work, we explain why this behavior should be attributed to model misestimation. We first prove that no method can guarantee performance beyond random chance without assumptions on which out-distributions are relevant. We then interrogate the
    Language English
    Publishing date 2022-07-04
    Publishing country United States
    Document type Journal Article
    ISSN 2640-3498
    ISSN (online) 2640-3498
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Book ; Online: Don't be fooled

    Jethani, Neil / Saporta, Adriel / Ranganath, Rajesh

    label leakage in explanation methods and the importance of their quantitative evaluation

    2023  

    Abstract: Feature attribution methods identify which features of an input most influence a model's output. Most widely-used feature attribution methods (such as SHAP, LIME, and Grad-CAM) are "class-dependent" methods in that they generate a feature attribution ... ...

    Abstract Feature attribution methods identify which features of an input most influence a model's output. Most widely-used feature attribution methods (such as SHAP, LIME, and Grad-CAM) are "class-dependent" methods in that they generate a feature attribution vector as a function of class. In this work, we demonstrate that class-dependent methods can "leak" information about the selected class, making that class appear more likely than it is. Thus, an end user runs the risk of drawing false conclusions when interpreting an explanation generated by a class-dependent method. In contrast, we introduce "distribution-aware" methods, which favor explanations that keep the label's distribution close to its distribution given all features of the input. We introduce SHAP-KL and FastSHAP-KL, two baseline distribution-aware methods that compute Shapley values. Finally, we perform a comprehensive evaluation of seven class-dependent and three distribution-aware methods on three clinical datasets of different high-dimensional data types: images, biosignals, and text.

    Comment: AISTATS 2023
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
    Subject code 004
    Publishing date 2023-02-24
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Book ; Online: Where to Diffuse, How to Diffuse, and How to Get Back

    Singhal, Raghav / Goldstein, Mark / Ranganath, Rajesh

    Automated Learning for Multivariate Diffusions

    2023  

    Abstract: Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality. For example, ... ...

    Abstract Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality. For example, extending the inference process with auxiliary variables leads to improved sample quality. While there are many such multivariate diffusions to explore, each new one requires significant model-specific analysis, hindering rapid prototyping and evaluation. In this work, we study Multivariate Diffusion Models (MDMs). For any number of auxiliary variables, we provide a recipe for maximizing a lower-bound on the MDMs likelihood without requiring any model-specific analysis. We then demonstrate how to parameterize the diffusion for a specified target noise distribution; these two points together enable optimizing the inference diffusion process. Optimizing the diffusion expands easy experimentation from just a few well-known processes to an automatic search over all linear diffusions. To demonstrate these ideas, we introduce two new specific diffusions as well as learn a diffusion process on the MNIST, CIFAR10, and ImageNet32 datasets. We show learned MDMs match or surpass bits-per-dims (BPDs) relative to fixed choices of diffusions for a given dataset and model architecture.
    Keywords Computer Science - Machine Learning ; Statistics - Machine Learning
    Subject code 670
    Publishing date 2023-02-14
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top