Paper proposes structured semantic perturbations to improve adversarial attacks.
problem Vulnerability of deep neural networks to adversarial attacks.
method Manipulates semantic attributes via disentangled latent codes.
result Demonstrates the effectiveness of structured semantic perturbations.
New method neutralizes gender bias in word embeddings without losing semantic information.
problem Gender biases in word embeddings trained on human-generated corpora.
method Latent Disentanglement and Counterfactual Generation with siamese auto-encoder and gradient reversal layer.
result Our method outperforms existing debiasing methods in preserving semantic information and neutralizing gender biases.
SEMASIA provides a large dataset of latent representations for model comparison.
problem Difficulty in comparing semantic structures across different neural network models.
method Collection of latent representations from 1700 pretrained models across various benchmarks.
result Consistent semantic organization across models and datasets.
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
problem Challenges in handling semantic and hierarchical structure in knowledge areas.
method Introduces a novel learner model that exploits semantic relatedness between knowledge components using a Wikipedia link graph.
result Achieves statistically significant improvements in predictive performance for educational engagement.
In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via latent topics. Because of their sequential nature, RNNs are good at capturing the local structure of a word sequence - both semantic and syn…
Enhances word embedding by transferring external knowledge.
problem Low-frequency words in semantic space.
method Latent Semantic Imputation (LSI) integrating graph theory and spectral embeddings.
result LSI generates reliable embedding vectors for low-frequency words.
Top2Vec finds topic vectors from documents and words without needing stop words or custom settings.
problem Topic modeling weaknesses, including needing known topics, stop words, and custom settings.
method Joint document and word semantic embedding to find topic vectors automatically.
result Top2Vec finds more informative and representative topics than probabilistic models.
This work provides uncertainty intervals for semantic latent variables in disentangled latent spaces.
problem Challenges in providing meaningful uncertainty quantification for semantic information in disentangled latent spaces.
method Uses quantile regression to output heuristic uncertainty intervals, calibrates these intervals to contain true latent values, and propagates them through the generator.
result Reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in image super-resolution and image completion.
Proposes Structuring AutoEncoders to learn structured latent spaces.
problem Traditional Autoencoders fail to discover semantic structure in raw data.
method Enhances traditional Autoencoders using weak supervision to form a structured latent space.
result Structured latent space allows for more efficient data representation and tasks like classification.
The study categorizes knowledge graph relations and explains their embedding representations.
problem Understanding how knowledge graph relation representations capture semantic information.
method Categorizing knowledge graph relations into three types and deriving explicit requirements for their representations.
result Empirical properties of relation representations and the performance of methods are justified by the analysis.
Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas. Compared to standard Latent Semantic Analysis which s…
This work prevents variational autoencoders from collapsing by adding an auxiliary decoder.
problem Variational autoencoders can collapse into autodecoders, losing semantic information.
method Adding an auxiliary decoder to regularize the latent space.
result Auxiliary decoders increase semantic information in the latent space and reconstructions.
Improved generalization with semantic perturbations using normalizing flows.
problem Overfitting in deep neural networks training.
method Use normalizing flows for generating semantically meaningful perturbations in latent space.
result Achieved 96.6% test accuracy on CIFAR-10 with ResNet-18, outperforming existing methods.
The abstract explains how word and relation representations capture semantic meaning.
problem Understanding how word and relation representations capture semantic meaning.
method Theoretical justification and extension of geometric relationships between word embeddings and knowledge graph representations.
result The geometric relationships between word embeddings correspond to semantic relations between words and entities in knowledge graphs.
In this tutorial, I will discuss the details about how Probabilistic Latent Semantic Analysis (PLSA) is formalized and how different learning algorithms are proposed to learn the model.
Low-dimensional vectors improve semantic understanding of music and language.
problem Noise in shared semantics due to individual brain biases.
method Jointly model multiple brains to learn low-dimensional vector embeddings.
result These embeddings outperform high-dimensional fMRI data in music and language classification.
Method interprets GAN latent space via latent variable correlation analysis.
problem Understanding the inner workings of GANs.
method Analyzing correlation between latent variables and semantic contents in generated images.
result A method for controllable semantic content generation in GANs.
New framework aligns latent representations over-the-air using intelligent metasurfaces.
problem Heterogeneous transmitter-receiver models produce misaligned latent representations in semantic communication.
method Intelligent metasurfaces (SIM) emulate supervised and zero-shot semantic aligners directly in the wave domain.
result SIMs achieve up to 90% task accuracy in high SNR regimes, robust to low SNR.
The paper explains how continuous language models can produce discrete, interpretable meanings.
problem Semantic collapse in continuous systems of large language models.
method Formalizing large language models as Continuous State Machines (CSMs) and analyzing the associated transfer operator.
result The leading eigenfunctions of the transfer operator induce a finite number of invariant meaning basins, explaining how continuous computation can produce discrete, interpretable semantics.
Entropy tracking reveals class commitment transitions in diffusion models.
problem Diffusion models lack reliable methods to detect semantic structure transitions.
method Tracking class-conditional entropy of latent variables.
result Entropy isolates noise regimes critical for semantic structure formation.
Improves GANs by sampling meaningful points from latent manifold.
problem Lack of semantic information in GANs' prior distribution.
method Local Coordinate Coding (LCC) for sampling and improved generator approximation.
result Improves GANs' performance in generating realistic data.
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the…
Intelligence emerges from stabilizing invariant cycles in memory.
problem Understanding the nature of intelligence and its emergence.
method Structural-dynamical account rooted in a topological closure law: \(\partial^2=0\).
result Memory-amortized inference (MAI) mechanism that implements SbS \(
ightarrow\) CCUP.
Improved genetic programming by optimizing mutation operators for continuous program search.
problem Small syntactic mutations in genetic programming can lead to unpredictable behavioral shifts.
method Learned a compact trading-strategy DSL, created a block-factorized embedding, and designed geometry-compiled mutation operators.
result Geometry-compiled mutation operators discover strong strategies using fewer evaluations and achieve higher Sharpe ratios.
We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data. Our model allows simultaneous inference of the number of binary latent variables, and their values. The latent variables preserve neighbourhood structure of the data in a sense that objects in the same semanti…
This research embeds data as discrete probability distributions in Wasserstein spaces, capturing semantic structures more effectively.
problem Limitations of Euclidean embeddings in capturing latent semantic structures.
method Learning embeddings into entropic Wasserstein spaces, capturing semantic information in Wasserstein distance.
result Wasserstein embeddings can embed a wider variety of metric structures with smaller distortion than Euclidean embeddings.
This work predicts and interpolates long-range videos using unsupervised landmarks.
problem Predicting and interpolating long-range video data with occlusions and appearance changes.
method Unsupervised latent structure inference followed by temporal prediction in a latent space.
result High-quality long-range video interpolation and extrapolation achieved through landmark representation.
Faster, context-aware topic modeling approach unveiled.
problem Slow and heavy preprocessing in topic modeling.
method Conceptualizes topics as independent axes, decomposes embeddings using ICA.
result 4.5x faster than BERTopic on average, with diverse and coherent topics.
A game helps users understand latent factors in recommender systems.
problem Users struggle to understand the latent factors in recommender systems.
method Presented an output-agreement game to represent latent factors.
result Collected outputs reflect real-world characteristics of latent factors.
Proposes a VAE with a discrete bottleneck for better text generation.
problem VAEs struggle with latent variable auto-regressive decoding in text generation.
method Introduces a discretized bottleneck to enforce latent feature matching in a compact space.
result Demonstrates improved text generation capabilities across various tasks.
Paper presents a framework for learning generative models with structured latent factors.
problem Learning controllable and generalizable representations of multivariate data with desired structural properties.
method The paper introduces a novel generative model framework that uses mask variables to model dependency structure and extends the multivariate information bottleneck theory.
result The framework learns semantically meaningful latent factors that reflect various desired structures and can automatically estimate dependency structure from data.
Improves clustering performance by mixing latent representations.
problem Finding well-defined clusters in data representations.
method Mixing Consistent Deep Clustering method that encourages realistic interpolations and semantic consistency.
result Improved clustering performance across various models and datasets.
Method infers domain-specific models without domain semantic descriptors.
problem Poor performance of standard supervised learning methods in unseen domains.
method Introduces latent domain vectors and neural networks for optimization.
result Inference of appropriate domain-specific models without semantic descriptors.
Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy. Recently, high-dimensional parametric models like neural networks have succeeded in building rich representations using either compressive, reconstructive or supervised criteria. However, the seman…
New algorithm finds minimal causal models for complex latent variables.
problem Learning causal structure in presence of latent variables and measurement dependencies.
method Graph theoretic edge clique cover problem, non-parametric algorithm.
result Minimality in minimal causal models implies specific properties.
NES optimizes discrete structured VAEs effectively without gradient propagation.
problem Learning high-dimensional discrete latent spaces in generative models.
method Natural Evolution Strategies (NES) for gradient-free optimization of discrete structures.
result NES effectively optimizes discrete structured VAEs, comparable to gradient-based methods.
iGCL preserves graph semantics in latent space augmentations.
problem Manual tuning of augmentation ratios and unexpected graph changes.
method iGCL uses a Variational Graph Auto-Encoder to learn augmentations in the latent space, optimizing an upper bound for contrastive loss.
result iGCL achieves state-of-the-art performance on graph-level and node-level tasks.
We improve conditional VAEs by incentivizing informative latent variables.
problem Structured-prediction tasks with one-to-many mappings.
method Modify latent variable model and introduce a multimodal prior.
result Significantly higher generalisation capability demonstrated on various datasets.
SAMI learns disentangled representations from data.
problem Learning disentangled representations from data.
method Combines diffusion models and VAEs to learn disentangled representations.
result SAMI learns disentangled representations that are interpretable and useful.
We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories ar…
Introduces PCG for better counterfactual explanations in vision models.
problem Ambiguity in latent-space optimization methods for counterfactual explanations.
method Constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric.
result PCG outperforms baselines and reveals hidden failure modes.
Unsupervised method discovers interpretable directions in GAN latent space.
problem Discovering interpretable directions in GAN latent space without supervision.
method Model-agnostic procedure to identify directions corresponding to semantic manipulations.
result Findings include directions for background removal and competitive saliency detection performance.
SOM-VQ tokenizes discrete models with semantic structure and navigable topology.
problem Lack of semantic structure in vector quantized representations limits interpretable human control.
method Combines vector quantization with Self-Organizing Maps to learn discrete codebooks with explicit topology.
result SOM-VQ produces more learnable token sequences and provides an explicit navigable geometry in code space.
Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods. This paper proposes a new generative model, a dynamic version of the log-linear topic model o…
CADD improves generative quality by augmenting discrete diffusion with continuous latent space.
problem Loss of semantic information between denoising steps in discrete diffusion models.
method Introduces a framework that augments discrete state space with a continuous latent space, allowing for graded, informative masked tokens.
result CADD improves generative quality across text generation, image synthesis, and code modeling.
The paper tests deep music embeddings for semantic consistency.
problem Ensuring deep music embeddings capture meaningful musical semantics.
method Proposes a systematic method to test deep music representations for semantic consistency, considering both input audio space and latent deep space.
result Distance consistency between related points is maintained in both input audio space and latent deep space.
VJE learns latent representations without contrastive learning, providing probabilistic semantics.
problem Learning latent representations without contrastive signals.
method VJE maximizes a symmetric conditional evidence lower bound (ELBO) on paired encoder embeddings, using a Student-t distribution on a polar representation.
result VJE outperforms standard non-contrastive baselines in ImageNet-1K, CIFAR-10/100, and STL-10.
Unsupervised framework learns latent codes for controllable generation.
problem Challenging to achieve controllable generation with GANs.
method Self-training iterative feedback from discriminator to generator.
result Better disentanglement and semantic meaningful latent codes.