This report to our stage 2 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for learning disentangled latent factors. We propose to train a variational autoencoder on regionally aggregated feature maps obtained from networks pretrained on the ImageNet database, utili…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “disentangled features”
Simple method disentangles content and style from pre-trained vision models.
problem Learning interpretable features in visual representations.
method Probabilistic linear entanglement model and simple disentanglement algorithm.
result Method provably disentangles content and style features.
This report to our stage 1 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for training VAEs leading to improved disentanglement compared to directly using the images. In particular, we propose to use regionally aggregated feature maps extracted from CNNs pretrained…
AAT separates robust and non-robust features without supervision.
problem Adversarial vulnerability and accuracy reduction in machine learning models.
method Adversarial Asymmetric Training (AAT) algorithm.
result Preserves accuracy and achieves better disentanglement than previous methods.
The paper defines and analyzes feature complexity in DNNs, proposing metrics for feature disentanglement and evaluation.
problem Understanding and quantifying the complexity of features learned by deep neural networks.
method Proposes a definition and disentanglement of feature complexity orders, introduces metrics for reliability and over-fitting evaluation.
result Establishes a relationship between feature complexity and DNN performance, and proposes a generic mathematical tool for network compression and knowledge distillation.
Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also …
Unsupervised mesh disentanglement separates identity and pose.
problem Geometric disentanglement for 3D deformable models.
method CFAN-VAE architecture using conformal factor and normal features.
result CFAN-VAE achieves state-of-the-art performance on unsupervised geometric disentanglement.
New method learns disentangled representations using Gromov-Monge maps.
problem Learning disentangled representations from unlabelled data.
method Introduces a novel approach based on Gromov-Monge maps to preserve geometric features while aligning data distributions.
result Demonstrates effectiveness on four benchmarks, outperforming other methods.
New framework for disentangling graph node and edge features.
problem Learning disentangled representations for attributed graphs with node and edge features.
method Proposes a novel variational objective and architecture for node and edge deconvolutions to disentangle latent factors.
result Demonstrates effectiveness of the proposed model and its extensions on synthetic and real-world datasets.
One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature encoding for the relevant task and thus lead to poor generalization of deep learnin…
IndiSeek learns disentangled representations by balancing independence and completeness.
problem Learning disentangled representations with mutual information in multi-modal data.
method Combines independence-enforcing objective with a reconstruction loss that bounds conditional mutual information.
result Demonstrates effectiveness on synthetic data, CITE-seq, and real-world multi-modal benchmarks.
New method disentangles feature importance scores in machine learning.
problem Misinterpretation of feature importance scores due to interactions and dependencies.
method Derive DIP (Disentangled Importance) decomposition of feature importance scores.
result DIP decomposition uniquely separates standalone contributions from interactions and dependencies.
A new method for disentangled representations without supervision.
problem Learning disentangled representations in unsupervised learning.
method Constr-DRKM, a deep kernel method with orthogonality constraints.
result Constr-DRKM performs similarly to β-VAE on disentanglement metrics.
The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis. State-of-the-art methods for disentangling feature representations rely on the presence of many labeled samples. In this work, we present a novel method for disentangling factors …
Proposes a framework for extracting consistent physiological features across users.
problem Variability of biosignals across different users and tasks.
method Adversarial feature extractor for disentangled universal representations.
result Up to 8.8% improvement in average accuracy of classification.
We analyze disentangled representations under a causal generative process, proposing new metrics and datasets.
problem Addressing fairness and interpretability through disentangled representations with a causal perspective.
method Work under a causal generative process, proposing new metrics and datasets to study disentanglement.
result Proposed metrics capture the desiderata of disentangled causal process.
Agents solving multi-task classification learn disentangled representations.
problem Creating interpretable world models from multi-task data.
method Optimal multi-task classification tasks, noise, evidence accumulation.
result Disentangled representations emerge in multi-task learning.
New algorithm disentangles latent features without strict assumptions.
problem Disentangling complex data-generating mechanisms into causally interpretable latent features.
method Linear CRL algorithm with topological ordering, pruning, and disentanglement.
result Recovering latent causal features up to an equivalence class under weaker assumptions.
Boxhead dataset tests autoencoder disentanglement in hierarchical data.
problem Evaluate disentanglement in hierarchical data.
method Introduced Boxhead dataset with hierarchically structured factors, evaluated autoencoder models.
result Hierarchical models outperform single-layer VAEs in disentangling factors.
LFD method improves text classification by making features clearer and less label-leaking.
problem Creating interpretable text representations that are both predictive and understandable.
method LFD method: proposes lexical and semantic features from contrastive text pairs, screens candidates using , and selects features by residual gain.
result LFD features achieve higher human-human and human-LLM agreement than baseline concepts and are less label-leaking.
DeepDIVE disentangles input into marginal and conditional distributions for multi-task learning.
problem Challenges in multi-task learning due to conflicting objectives.
method Inspired by probability theory, DeepDIVE uses a variational autoencoder with disentangled features and cross-attention mechanism.
result DeepDIVE disentangles input and improves forecast accuracy compared to baseline models.
CVAE learns disentangled and coupled representations without prior knowledge.
problem Learning disentangled and coupled representations in latent space.
method Introduces CVAE, a self-supervised VAE that factorizes posterior and uses Gaussian copula for dependencies.
result Demonstrates strong effect in enhancing disentangled representation learning.
The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative approach is to have perturbations in the latent space. However, such perturbations ar…
New method disentangles style features from data augmentations.
problem Difficulty in deducing which data attributes are 'style' and should be discarded.
method Structured data augmentation with multiple style embedding spaces, maximizing joint entropy.
result Empirically demonstrates benefits on synthetic and real-world data.
This work improves disentanglement in latent space models without sacrificing generation quality.
problem Trade-off between disentanglement and generation quality in latent space models.
method Manifold optimization with a sum of autoencoder and PCA reconstruction errors, on the Stiefel manifold.
result Improves disentanglement without sacrificing generation quality.
ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mappingcs.LG
ICAM creates interpretable feature attribution maps for brain images.
problem Challenges in predicting class relevance from brain images due to heterogeneity and background variation.
method A VAE-GAN framework for disentangling class relevance from background features.
result FA maps generated by ICAM outperform baseline methods and support phenotype variation exploration.
The paper formalizes criteria for non-spurious and disentangled representations using causal methods.
problem Formalizing criteria for non-spurious and disentangled representations in representation learning.
method Causal perspective, counterfactual quantities, observable consequences of causal assertions.
result Computable metrics for assessing representation learning based on observed data.
InfoQGAN uses mutual information to improve QGANs, overcoming mode collapse and feature disentanglement issues.
problem Mode collapse and lack of feature control in QGANs.
method Integrates InfoGAN principles with variational quantum circuit, classical discriminator, and MINE for mutual information optimization.
result InfoQGAN effectively mitigates mode collapse and achieves robust feature disentanglement.
Adversarial transfer learning improves stress assessment across users.
problem Transfer learning challenges in physiological biosignals.
method Disentangled nuisance-robust representations using adversarial networks.
result Adversarial framework enhances cross-subjects stress assessment.
Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a more compact and explainable representation of the data. In this paper, we introdu…
Disentangled encoding is an important step towards a better representation learning. However, despite the numerous efforts, there still is no clear winner that captures the independent features of the data in an unsupervised fashion. In this work we empirically evaluate the performance of six unsupervised disentangleme…
A framework for disentangling class-related and class-independent factors in data.
problem Learning disentangled representations in variational autoencoders.
method Attention mechanism in latent space, mixture models, Bhattacharyya coefficient, semi-supervised training.
result Disentangles class-related and class-independent factors of variation.
Disentangling the independently controllable factors of variation by interacting with the worldstat.ML
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that…
Unified framework for disentangled VAEs improves latent space interpretability.
problem Challenges in evaluating and interpreting latent representations, especially for diverse data types.
method Unified bfVAE framework, FVH-LT, DBSR-LS, GAS, LSSI.
result bfVAE provides more favorable trade-off between disentanglement and reconstruction.
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelingstat.ML
Improves disentangled representation learning with multi-stage modeling.
problem Trade-off between disentanglement and reconstruction quality in autoencoders.
method Penalty-based disentanglement learning followed by detail information modeling.
result Higher reconstruction quality than state-of-the-art methods with equivalent disentanglement.
Generative modeling of 3D shapes has become an important problem due to its relevance to many applications across Computer Vision, Graphics, and VR. In this paper we build upon recently introduced 3D mesh-convolutional Variational AutoEncoders which have shown great promise for learning rich representations of deformab…
New findings show disentangled latent representations are not enough for robust compositional generalization.
problem Deep learning models struggle with compositional generalization, especially in out-of-distribution samples.
method Investigated a 2D Gaussian generation task with fully disentangled inputs, then forced disentangled latent representations into full-dimensional output space.
result Forcing disentangled latent representations into full-dimensional output space enables robust compositional generalization.
Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representationscs.LG
In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relational reasoning problems derived from Raven Progressive Matrices. We show that the latent representations, learned by unsupervised training …
We investigate the effects of the unsupervised pre-training method under the perspective of information theory. If the input distribution displays multiple views of the supervision, then unsupervised pre-training allows to learn hierarchical representation which communicates these views across layers, while disentangli…
Music FaderNets learns high-level musical qualities from low-level attributes.
problem Learning high-level musical qualities from limited data and subjective labels.
method Model low-level attributes through feature disentanglement and latent regularization; infer high-level features from low-level representations using GM-VAEs.
result Model successfully learns intrinsic relationships between high-level features and low-level attributes with minimal labeled data.
We present a deep generative model that learns disentangled static and dynamic representations of data from unordered input. Our approach exploits regularities in sequential data that exist regardless of the order in which the data is viewed. The result of our factorized graphical model is a well-organized and coherent…
PIMA autoencoders discover shared features in multimodal scientific data.
problem Discovering shared information in high-throughput scientific datasets.
method Physics-informed multimodal autoencoders (PIMA) with Gaussian mixture prior and product of experts formulation.
result Accurate cross-modal inference between images and mechanical stress-strain response in lattice metamaterials.
New framework for disentangling features from noisy data.
problem Disentangling identifiable features from noisy data.
method Structured Nonlinear Independent Component Analysis (SNICA).
result Identifiability holds even in the presence of noise of unknown distribution.
Unified predictive uncertainty disentangled using deep split ensembles.
problem Understanding and quantifying uncertainty in NNs for real-world applications.
method Deep split ensemble approach using multivariate Gaussian mixture model.
result Inherently well-calibrated models with high flexibility to group features.
New metrics assess disentanglement in generative models.
problem Measuring disentanglement in generative models is challenging.
method Introduces manifold entropic metrics based on information theory.
result Ranking of model architectures and training procedures.
New method disentangles high-order effects in feature importance.
problem Quantifying cooperative effects in feature importance.
method Adaptive Leave One Covariate Out (LOCO) method to decompose LOCO into two-body and higher-order components.
result Decomposes LOCO into two-body and higher-order components, highlighting synergistic and redundant effects.
CausalVAE learns causal relationships in VAE models for better data disentanglement.
problem Learning disentanglement of independent factors from observational data.
method CausalVAE framework with a Causal Layer to transform exogenous factors into causal endogenous ones.
result CausalVAE learns semantically interpretable causal representations and accurately identifies their DAG structure.
Method separates data into class and style factors using semi-supervised learning.
problem Separating generative factors of data into class and style vectors.
method Independent Vector Variational Autoencoders with semi-supervised learning and independence term.
result Improves classification performance and generation controllability.