We create interpretable word embeddings through sparse coding.
problem Difficult to interpret word embeddings in natural language processing.
method Transform pretrained dense word embeddings into sparse embeddings through sparse coding.
result Sparse embeddings are more interpretable and achieve good performance.
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.
POLAR framework interprets word embeddings using polar opposites.
problem Lack of interpretability in pre-trained word embeddings.
method Adopt semantic differentials and polar opposites to transform embeddings.
result Interpretable word embeddings maintain performance comparable to original embeddings.
Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is to visualize them. We present the Embedding Projector, a tool for interactive v…
New method interprets deep embeddings for diabetes patient clustering.
problem Interpreting deep embeddings for disease progression.
method Patient clustering approach using deep embeddings.
result Clinically meaningful insights into diabetes progression patterns.
Word embeddings have demonstrated strong performance on NLP tasks. However, lack of interpretability and the unsupervised nature of word embeddings have limited their use within computational social science and digital humanities. We propose the use of informative priors to create interpretable and domain-informed dime…
A new method for document network embedding interprets and generalizes well.
problem Lack of interpretability and generalization to new documents in existing methods.
method Introduces Topic-Word Attention (TWA) and Inductive Document Network Embedding (IDNE) to generate document representations.
result Achieves state-of-the-art performance on various networks and produces meaningful representations.
New algorithm improves interpretability in sequence classification.
problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.
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.
Unified interpretation of softmax cross-entropy and negative sampling for knowledge graph embedding.
problem Lack of theoretical relationship between softmax cross-entropy and negative sampling loss functions in knowledge graph embedding.
method Used Bregman divergence to provide a unified interpretation of the two loss functions.
result Theoretical findings for fair comparison of softmax cross-entropy and negative sampling are derived.
DAOR efficiently embeds graphs without tuning, improving speed and interpretability.
problem Graph embedding limitations in resource usage, interpretability, and parameter dependence.
method DAOR uses community detection to produce robust, interpretable embeddings without manual tuning.
result DAOR outperforms state-of-the-art techniques on node classification and link prediction.
Knowledge bases are employed in a variety of applications from natural language processing to semantic web search; alas, in practice their usefulness is hurt by their incompleteness. Embedding models attain state-of-the-art accuracy in knowledge base completion, but their predictions are notoriously hard to interpret. …
In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide…
CAMEL enhances manifold embedding and learning with curvature metrics.
problem High-dimensional data classification, dimension reduction, and visualization.
method CAMEL uses a Riemannian manifold with curvature metrics for enhanced expressibility and interpretability.
result CAMEL outperforms state-of-the-art methods on high-dimensional datasets.
Generating high-quality and interpretable adversarial examples in the text domain is a much more daunting task than it is in the image domain. This is due partly to the discrete nature of text, partly to the problem of ensuring that the adversarial examples are still probable and interpretable, and partly to the proble…
Minimal token perturbations reveal how Transformer models process information.
problem Understanding information propagation in Transformer models for interpretability.
method Study of minimal token perturbations on embedding space.
result Rare tokens cause larger shifts, and input information mixes deeper.
VICE embeds concepts in a vector space using human data.
problem Developing numerical models for mental representations of object concepts.
method Variational Interpretable Concept Embeddings (VICE) using variational inference and triplet odd-one-out task data.
result VICE outperforms SPoSE at predicting human behavior and provides more reproducible object representations.
A new HP model balances interpretability and flexibility for EHR event sequences.
problem Balancing interpretability and flexibility in modeling diagnostic event sequences.
method Proposes a neural network-based HP with flexible impact kernel and transformer layers.
result Accurately recovers impact functions, competitive performance, and clinically meaningful interpretation.
TransINT embeds KGs by preserving implication rules, outperforming existing methods.
problem Embedding KGs while preserving relation implications for better access and analysis.
method Isomorphic intersections of linear subspaces with shared parameters for missing facts.
result Significant performance improvement in link prediction and triple classification.
Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic Model (ETM), a generative model of documents that marries traditional topic models …
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
problem Inability of concept-based models to provide transparent decision processes.
method DCR uses neural networks to build syntactic rule structures using concept embeddings and executes these rules on concept truth degrees.
result DCR improves interpretability by up to 25% on challenging benchmarks and discovers meaningful logic rules.
A novel GP architecture, Thin and Deep GP, learns lower-dimensional representations without losing interpretability.
problem Challenges in selecting appropriate kernel for Gaussian processes.
method Proposes a novel synthesis of deep and shallow GP approaches, parameterizing lengthscale in a way that maintains interpretability and learns lower-dimensional embeddings.
result TDGP discovers lower-dimensional manifolds in input data, performs well in benchmark datasets, and behaves well with increasing layers.
Dimensionality reduction (DR) on the manifold includes effective methods which project the data from an implicit relational space onto a vectorial space. Regardless of the achievements in this area, these algorithms suffer from the lack of interpretation of the projection dimensions. Therefore, it is often difficult to…
Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. However, similarity is a multi-dimensional concept that varies from individual to individual. Ex…
Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the image processing field to the input word embedding space instead of the discrete…
AMES framework selects optimal embedding space for latent graph inference.
problem No principled method for choosing the best embedding space for latent graph inference.
method Differentiable AMES framework using backpropagation to select optimal embedding space.
result Consistently achieves comparable or superior results across multiple datasets.
Node embedding is the task of extracting informative and descriptive features over the nodes of a graph. The importance of node embeddings for graph analytics, as well as learning tasks such as node classification, link prediction and community detection, has led to increased interest on the problem leading to a number…
Study geodesic properties of time series data using Wasserstein metric.
problem Modeling nonlinear time series with transport-based metrics.
method Generalized Wasserstein metric and signed cumulative distribution transforms.
result Geodesic properties provide added interpretability and robustness in time series classifiers.
A framework for stable dynamic network embeddings using static methods.
problem Dynamic network embedding in a nascent field.
method Using static network embedding methods on dilated unfolded adjacency matrices.
result Stable embeddings that preserve latent node behavior across time.
We break down transformer embeddings into interpretable components revealing hidden geometric structures.
problem Understanding the hidden geometry and interpretability of transformer models.
method Decomposed transformer embeddings into position, context, and residual components.
result Pervasive mathematical structure in transformer embeddings, including position and context vectors.
This work analyzes PPR-based node embeddings and their topological information.
problem Understanding and interpreting PPR-based node embeddings.
method Unified framework and two methods for topology recovery.
result PPR-based embeddings maintain more topological information than random walk-based embeddings.
In this paper we introduce score embedding, a neural network based model to learn interpretable vector representations for words. Score embedding is a supervised method that takes advantage of the labeled training data and the neural network architecture to learn interpretable representations for words. Health care has…
Combines OT and PCA for DR, preserving clusters.
problem Analyzing high-dimensional data with global dependencies.
method Optimal transport (OT) for minimizing reconstruction error, combined with PCA.
result Effective preservation of high-dimensional clusters in embeddings.
OracleAD detects multivariate time series anomalies without labels.
problem Rare and unlabeled multivariate time series anomalies.
method OracleAD encodes past sequences into causal embeddings, projects them into a latent space, and identifies anomalies based on deviations from a stable latent structure.
result OracleAD achieves state-of-the-art results and is interpretable.
A new method simplifies HLLE for better robustness.
problem Improving robustness of Hessian locally linear embedding.
method Replacing Hessian with arbitrary weights and modifying manifold dimension.
result Achieved a new LLE-type method called tangential LLE.
Models use embeddings and attention for better claim severity prediction.
problem Improving predictive modeling of claim severity with categorical data.
method Developed neural networks and attention-based architectures with embeddings.
result Attention-based models enhance predictive performance with contextual augmentation.
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.
Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using Singular Value Decomposition (SVD), may incur loss of corpus information. In addi…
LOT framework embeds high-dimensional cell data into interpretable Euclidean space.
problem Lack of interpretable methods for high-dimensional cell data.
method Adapts Linear Optimal Transport (LOT) to irregular point clouds.
result Accurate and interpretable classification and synthetic data generation.
The interpretability of machine learning, particularly for deep neural networks, is crucial for decision making in real-world applications. One approach is replacing the un-interpretable machine learning model with a surrogate model, which has a simple structure for interpretation. Another approach is understanding the…
With the rising interest in graph representation learning, a variety of approaches have been proposed to effectively capture a graph's properties. While these approaches have improved performance in graph machine learning tasks compared to traditional graph techniques, they are still perceived as techniques with limite…
By representing words with probability densities rather than point vectors, probabilistic word embeddings can capture rich and interpretable semantic information and uncertainty. The uncertainty information can be particularly meaningful in capturing entailment relationships -- whereby general words such as "entity" co…
Protein Thoughts interprets protein interactions with clear reasoning, improving prediction accuracy.
problem Lack of mechanistic justification in protein-protein interaction predictions.
method Interpretable search problem reformulation, hypothesis-guided entropy-regularized Tree-of-Thoughts search, embedding-space flow matching.
result Improves mean best-binder rank from 47.7 to 11.2 on SHS148k benchmark.
The transition amplitudes between coherent states on a coherent state manifold are expressed in terms of the embedding of the coherent state manifold into a projective Hilbert space. Consequences for the dimension of projective Hilbert space and a simple geometric interpretation of Calabi's diastasis follows.
MPVAE learns latent embeddings and label correlations for multi-label classification.
problem Challenging task of predicting multiple targets with label correlations.
method Proposes MPVAE, a novel framework that learns latent embedding spaces and label correlations using a Multivariate Probit model.
result MPVAE outperforms state-of-the-art methods on various application domains and is robust under noisy settings.
LIFE framework improves model accuracy and interpretability.
problem Achieving high prediction accuracy and interpretability in neural networks.
method Three-step process: subset definition, feature creation, and linear model combination.
result LIFE consistently outperforms other models in prediction accuracy and interpretability.
We present a novel spectral embedding of graphs that incorporates weights assigned to the nodes, quantifying their relative importance. This spectral embedding is based on the first eigenvectors of some properly normalized version of the Laplacian. We prove that these eigenvectors correspond to the configurations of lo…
Study evaluates interpretability of time series foundation models' latent spaces.
problem Improving interpretability of latent spaces in time series models for visual analytics.
method Evaluated MOMENT family of transformer-based models on five datasets, fine-tuning for performance.
result Fine-tuning improved latent space clarity but limited interpretability remained.