Interpretable representations improve explainable AI by translating complex data into understandable concepts.
problem Many explainers use interpretable representations but overlook their full potential and assumptions.
method An in-depth analysis of interpretable representations for tabular, image, and text data, identifying strengths, weaknesses, and desiderata.
result Linear model quantifies interpretable concepts' influence on black-box predictions, revealing their explanatory properties and manipulability.
DiSeNE generates interpretable node embeddings without supervision.
problem Lack of interpretability in unsupervised node embeddings.
method Disentangled representation learning with novel objective functions and metrics.
result DiSeNE produces interpretable node embeddings aligned with graph structure.
Develops an ordinal-similarity framework for scalable and interpretable representation alignment.
problem Measuring representation similarity in large datasets.
method Triplet and Quadruplet Similarity Indices.
result Demonstrates inherent interpretability, robustness to outliers, and computational efficiency.
FLANs process each feature separately for better interpretability.
problem Need for interpretable machine learning models in critical scenarios.
method Feature-wise latent representations summed for prediction.
result FLANs enhance interpretability without sacrificing performance.
High-dimensional time series are common in many domains. Since human cognition is not optimized to work well in high-dimensional spaces, these areas could benefit from interpretable low-dimensional representations. However, most representation learning algorithms for time series data are difficult to interpret. This is…
Drug repositioning is an attractive cost-efficient strategy for the development of treatments for human diseases. Here, we propose an interpretable model that learns disease self-representations for drug repositioning. Our self-representation model represents each disease as a linear combination of a few other diseases…
Unified framework interprets SSL models, revealing biases.
problem Interpreting black-box SSL models for transparency.
method KREPES framework using Representer Landmarks and Nyström approximation.
result Direct audit of SSL latent space without supervision.
End-to-end learnable network for safer self-driving with interpretable intermediate representations.
problem Safe motion planning for self-driving vehicles.
method Differentiable semantic occupancy representation for cost calculation in motion planning.
result Significantly outperforms state-of-the-art planners in imitating human behaviors and producing safer trajectories.
SENA-discrepancy-VAE interprets latent causal factors in biological pathways.
problem Interpreting latent causal factors in biological pathways.
method SENA-discrepancy-VAE, a model based on discrepancy-VAE, that produces interpretable latent causal factors.
result Sena-discrepancy-VAE achieves comparable predictive performance with non-interpretable counterparts while providing biologically meaningful causal factors.
New methods improve feature extraction and representation quality in supervised and unsupervised DR.
problem Statistical dependence, data diversity, contrast, and interpretability in conventional DR methods.
method Combines linear and nonlinear formulations for three new independence criteria.
result Significant improvements in contrast, accuracy, and interpretability over baselines.
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…
Paper develops a framework for learning interpretable representations of sequential decision behavior.
problem Obtaining a transparent description of existing behavior.
method Inverse decision modeling framework, formalizing both forward and inverse problems.
result Learning interpretable representations of behavior, including suboptimal actions, biased beliefs, and imperfect knowledge.
Proposes a method to learn invariant representations for interpretability and fairness.
problem Learning invariant representations to achieve interpretability in algorithmic fairness.
method Adversarially trained model with null-sampling procedure to produce invariant representations in the data domain.
result Shows effectiveness on image and tabular datasets.
Graph representations have increasingly grown in popularity during the last years. Existing representation learning approaches explicitly encode network structure. Despite their good performance in downstream processes (e.g., node classification, link prediction), there is still room for improvement in different aspect…
Unified approach to learn interpretable concepts from data.
problem Building interpretable machine learning models and highly-performing foundation models.
method Relating causal representation learning and foundation models, defining concepts and proving their recoverability.
result Provable recovery of human-interpretable concepts from diverse data.
TIME network simplifies complex physical processes with interpretable models.
problem Challenges in learning coupled dynamic processes from multiple observations.
method Fully convolutional architecture capturing invariant domain structure.
result Robust and transparent in capturing process kernels and anomalies.
CRL uses causality to build interpretable AI models from complex data.
problem Interpreting deep neural networks' implicit representations.
method Causal representation learning (CRL) synthesizing latent variable models, causal graphical models, and nonparametric statistics.
result CRL can improve interpretability of generative AI models.
VQShape learns interpretable time-series representations and achieves comparable performance to specialist models.
problem Lack of interpretability in existing time-series models.
method Vector quantization of time-series data into abstracted shapes.
result VQShape achieves comparable performance to specialist models in classification tasks.
Geometric interpretation of Fock-Goncharov positivity and disk stabilization in symmetric space.
problem Understanding Fock-Goncharov positivity and its geometric implications.
method Geometric interpretation and bending deformations of Fuchsian representations.
result Stabilization of a uniform Finsler quasi-convex disk in the symmetric space.
A new algorithm identifies interpretable network representations via subgraph count statistics.
problem Interpreting network-valued data samples.
method Principal Component Analysis for Networks (PCAN) and its fast sampling-based version (sPCAN).
result The PCAN and sPCAN methods provide informative and discriminatory features for network samples.
Learning interpretable representations of data remains a central challenge in deep learning. When training a deep generative model, the observed data are often associated with certain categorical labels, and, in parallel with learning to regenerate data and simulate new data, learning an interpretable representation of…
Unified approach for interpretable regression with flexible modeling.
problem Combining predictive adaptivity with interpretability in heterogeneous data.
method Combining random Fourier features, spectral feature map, principal component analysis, Gaussian mixture model, and cluster-specific generalized additive models.
result Consistently improves upon classical and black-box models across benchmark datasets.
Geometric framework detects concept frustration between human concepts and machine representations.
problem Aligning human concepts with machine learning representations.
method Geometric framework and similarity measures for detecting concept frustration.
result Concept frustration affects machine learning model performance and reorganizes learned concept representations.
NGSLL combines DNN accuracy with linear model interpretability.
problem Combining high accuracy of DNNs with interpretability of linear models.
method Neural generators of sparse local linear models (NGSLL) using DNNs to approximate non-linear functions.
result Effective in real-world datasets, achieving high predictive performance and interpretability.
Equivariant neural networks use symmetry to interpret complex data.
problem Interpreting and understanding the behavior of equivariant neural networks.
method Decompose layers into simple representations and analyze nonlinear activation functions.
result Equivariant neural networks can be interpreted using a filtration generalizing Fourier series.
We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluation. First, we characterize the concept "disentangled representations" used in supervised and unsupervised methods along three dimensions-in…
Prototype-based methods are of the particular interest for domain specialists and practitioners as they summarize a dataset by a small set of representatives. Therefore, in a classification setting, interpretability of the prototypes is as significant as the prediction accuracy of the algorithm. Nevertheless, the state…
In this paper we investigate the virtual string links via a probabilistic interpretation. This representation can be used to distinguish some virtual string links from classical string links. In order to study the algebraic structure behind this probabilistic interpretation we introduce the notion of virtual flat biqua…
Shallow trees in ensemble models make models more interpretable and sometimes better.
problem Lack of transparency in high-performing tree ensemble models.
method Developed an interpretation algorithm to convert tree ensembles into functional ANOVA representations. Proposed strategies to enhance interpretability.
result Shallow trees in ensemble models can lead to better generalization performance and improved interpretability.
Document network embedding aims at learning representations for a structured text corpus i.e. when documents are linked to each other. Recent algorithms extend network embedding approaches by incorporating the text content associated with the nodes in their formulations. In most cases, it is hard to interpret the learn…
To study how mental object representations are related to behavior, we estimated sparse, non-negative representations of objects using human behavioral judgments on images representative of 1,854 object categories. These representations predicted a latent similarity structure between objects, which captured most of the…
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
New method enforces encoder sparsity in HPF for more interpretable feature selection.
problem Lack of encoder sparsity in HPF leads to lack of column-clustering property.
method Enforces encoder sparsity using a generalized additive model (GAM).
result Gains ability to perform feature selection and relates each representation to original features.
Interpretable text-response modelling for structured outcomes
problem Predicting structured responses alongside textual data
method Joint non-negative matrix factorisation and binomial regression
result Recovering stable response-relevant textual signals
Scattering representations simplify SBI for images without extra compression.
problem Efficiently performing simulation-based inference on images with limited data.
method Use scattering representations for compression and learning, combined with spatial averaging and expressive density estimators.
result Scattering representations provide more information than traditional methods, without requiring additional simulations.
Hybrid model learns interpretable meal-level glycemic control.
problem Lack of flexible, interpretable meal-level glycemic control methods.
method Hybrid variational autoencoder grounding latent space to mechanistic differential equation.
result Unsupervised representation discovers separation between individuals based on disease severity.
The paper studies how neural policies can be interpreted using decision trees.
problem Understanding how machine learning controllers make decisions in complex environments.
method The approach involves disentangled representation using decision trees to interpret neural policies.
result The paper shows that disentanglement of learned neural dynamics improves interpretability.
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent varia…
WeLa-VAE learns interpretable disentangled representations with weak supervision.
problem Learning disentangled representations without strong supervision.
method Variational inference framework with shared latent variables and modified variational lower bound.
result WeLa-VAE learns alternative disentangled representations (polar) from weak labels (distance and angle) without refined supervision.
This paper proposes a hierarchical, fine-grained and interpretable latent variable model for prosody based on the Tacotron 2 text-to-speech model. It achieves multi-resolution modeling of prosody by conditioning finer level representations on coarser level ones. Additionally, it imposes hierarchical conditioning across…
i-cNRL learns network differences with interpretability.
problem Comparing unique network characteristics.
method Contrastive network representation learning (cNRL) integrating machine learning schemes.
result i-cNRL reveals unique network patterns with interpretability.
In 1990, Hitchin's proved a component of the space of representations of a surface group in SL(n,R) is homeomorphic to a ball. For n=2,3 this component has been identified with the holonomies of geometric structures (hyperbolic for n=2, or real projective for n=3). In the preprint "Anosov flows, Surface groups and Curv…
Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation. It is possible that the mapping between this new representation and our original data matrix contains rather complex hierarchical information with implicit lo…
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 κ, 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.
A new framework for fair representation learning using correction vectors.
problem Learning fair representations that are independent of sensitive features.
method Introducing correction vectors to neural network features for fair representation learning.
result The approach does not impact performance while ensuring fairness.
New model combines neural networks and embeddings for better choice modeling interpretability.
problem Limited behavioral insights in embedding representations for categorical variables.
method Combines discrete choice models and neural networks using embeddings for interpretability.
result Proposed models deliver state-of-the-art predictive performance while preserving interpretability.
Improved VAE learns disentangled representations with less supervision.
problem Learning disentangled representations is challenging.
method Semi-supervised disentanglement learning with label replacement.
result Significant improvement in disentanglement with minimal supervision.
The time series classification literature has expanded rapidly over the last decade, with many new classification approaches published each year. The research focus has mostly been on improving the accuracy and efficiency of classifiers, while their interpretability has been somewhat neglected. Classifier interpretabil…