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.
Proposes priors for interpretable word embeddings.
Method interprets GAN latent space via latent variable correlation analysis.
SEMASIA provides a large dataset of latent representations for model comparison.
This work shows how transformers use multi-concept word semantics for efficient in-context learning.
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 work explains how linear representations in large language models arise from training objectives and gradient descent.
We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different, standard supervised learning methods perform poorly. Zero-shot domain adaptation attemp…
This work provides uncertainty intervals for semantic latent variables in disentangled latent spaces.
Improves biomedical entity linking with latent type modeling.
Enhanced ontology learning from text improves question-answering systems.
RCAV quantifies model sensitivity to semantic concepts, improving interpretability methods.
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
Paper proposes structured semantic perturbations to improve adversarial attacks.
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…
New method neutralizes gender bias in word embeddings without losing semantic information.
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.
Service robots benefit from encoding information in semantically meaningful ways to enable more robust task execution. Prior work has shown multi-relational embeddings can encode semantic knowledge graphs to promote generalizability and scalability, but only within a batched learning paradigm. We present Incremental Se…
The paper explores how AI systems use information geometry to encode semantic structure.
Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information. For example, variational autoencoders with autoregressive decoders often collapse into autodecoders, where they learn to ignore the encoder input. In th…
We developed a caching method to speed up concept learning in complex knowledge bases.
New framework aligns latent representations over-the-air using intelligent metasurfaces.
Top2Vec finds topic vectors from documents and words without needing stop words or custom settings.
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…
The paper tests semantic importance in opaque models using betting.
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the latent variables such as standard normal distribution, thereby restricting its appli…
FCA2VEC embeds formal concept analysis data for large datasets.
In an effort to understand the meaning of the intermediate representations captured by deep networks, recent papers have tried to associate specific semantic concepts to individual neural network filter responses, where interesting correlations are often found, largely by focusing on extremal filter responses. In this …
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…
In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term "representative" is in itself challenging to define, and various tasks require different granularities of concepts. In this paper, we aim to model concepts that are sparse over the voca…
We present a novel method named Latent Semantic Imputation (LSI) to transfer external knowledge into semantic space for enhancing word embedding. The method integrates graph theory to extract the latent manifold structure of the entities in the affinity space and leverages non-negative least squares with standard simpl…
Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things. We investigate …
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
Improved generalization with semantic perturbations using normalizing flows.
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.
Unsupervised method discovers interpretable directions in GAN latent space.
CADD improves generative quality by augmenting discrete diffusion with continuous latent space.
We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we detect hierarchical cluster structures in feature space. This is visualized as heat m…
Unsupervised framework learns latent codes for controllable generation.
We would like to learn a representation of the data which decomposes an observation into factors of variation which we can independently control. Specifically, we want to use minimal supervision to learn a latent representation that reflects the semantics behind a specific grouping of the data, where within a group the…
An increasing number of people are using online social networking services (SNSs), and a significant amount of information related to experiences in consumption is shared in this new media form. Text mining is an emerging technique for mining useful information from the web. We aim at discovering in particular tweets s…
EigenGAN discovers interpretable dimensions in GAN layers for semantic control.
Linear Discriminant Analysis (LDA) is a well-known method for dimensionality reduction and classification. Previous studies have also extended the binary-class case into multi-classes. However, many applications, such as object detection and keyframe extraction cannot provide consistent instance-label pairs, while LDA …
New hashing method improves document retrieval precision.
Concept modulation models unify identifiability and extrapolation in conditional latent variable models.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
Improved scalability and interpretability in training data attribution.
Multimodal sensory data resembles the form of information perceived by humans for learning, and are easy to obtain in large quantities. Compared to unimodal data, synchronization of concepts between modalities in such data provides supervision for disentangling the underlying explanatory factors of each modality. Previ…