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.
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
Many models learn representations of knowledge graph data by exploiting its low-rank latent structure, encoding known relations between entities and enabling unknown facts to be inferred. To predict whether a relation holds between entities, embeddings are typically compared in the latent space following a relation-spe…
Recent advances in Neural Variational Inference allowed for a renaissance in latent variable models in a variety of domains involving high-dimensional data. While traditional variational methods derive an analytical approximation for the intractable distribution over the latent variables, here we construct an inference…
Paper presents new algorithms for causal discovery with latent variables and overlapping datasets.
In most cases deep learning architectures are trained disregarding the amount of operations and energy consumption. However, some applications, like embedded systems, can be resource-constrained during inference. A popular approach to reduce the size of a deep learning architecture consists in distilling knowledge from…
Recent advances in analysis of subband amplitude envelopes of natural sounds have resulted in convincing synthesis, showing subband amplitudes to be a crucial component of perception. Probabilistic latent variable analysis is particularly revealing, but existing approaches don't incorporate prior knowledge about the ph…
New method uses cycle consistency to enforce invariance in latent space.
Proposes a method to derive knowledge graphs from EHR data.
End-to-end framework learns precise disparity for activity recognition.
SLED improves factuality in LLMs without external knowledge.
Bayesian framework integrates prior and data knowledge for nonlinear dynamical systems.
New framework transfers latent knowledge from weak to strong models.
spex-LVM infers interpretable latent factors from biomedical data.
The paper proposes a deep generative model for complex disease trajectories.
In this work, we propose a method for learning driver models that account for variables that cannot be observed directly. When trained on a synthetic dataset, our models are able to learn encodings for vehicle trajectories that distinguish between four distinct classes of driver behavior. Such encodings are learned wit…
TASID learns policies in high-dimensional settings with abstract simulator knowledge.
MuVI models multi-view data with structured sparsity, integrating domain knowledge.
Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Us…
Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be "trained" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges…
New approach identifies latent properties from mechanisms, not just data.
DBULL learns new clusters without forgetting past knowledge in streaming unlabelled data.
The abstract explains how word and relation representations capture semantic meaning.
Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning from piece-wise stationary visual data: Variational Autoencoder with Shared Emb…
Hybrid models combine domain knowledge and data-driven learning for Earth observation.
Generative models use Riemannian manifolds to improve latent space interpretation.
Transfer learning for bandits with latent Lipschitz continuity.
Many predictive tasks, such as diagnosing a patient based on their medical chart, are ultimately defined by the decisions of human experts. Unfortunately, encoding experts' knowledge is often time consuming and expensive. We propose a simple way to use fuzzy and informal knowledge from experts to guide discovery of int…
We analyze the necessary and sufficient conditions for exact inference of a latent model. In latent models, each entity is associated with a latent variable following some probability distribution. The challenging question we try to solve is: can we perform exact inference without observing the latent variables, even w…
Study improves interpretability in generative models by disentangling latent variables in scientific datasets.
Enhances OOD detection using latent diffusion for more robust and efficient training.
New insights into continual learning with task similarity.
AGFN improves causal discovery by integrating expert feedback and handling latent confounding.
Random geometric graphs are a popular choice for a latent points generative model for networks. Their definition is based on a sample of points on the Euclidean sphere~ which represents the latent positions of nodes of the network. The connection probabilities between the node…
Knowledge graphs, on top of entities and their relationships, contain other important elements: literals. Literals encode interesting properties (e.g. the height) of entities that are not captured by links between entities alone. Most of the existing work on embedding (or latent feature) based knowledge graph analysis …
Observed associations in a database may be due in whole or part to variations in unrecorded (latent) variables. Identifying such variables and their causal relationships with one another is a principal goal in many scientific and practical domains. Previous work shows that, given a partition of observed variables such …
New method identifies latent variables with sparse perturbations.
Bayesian model enhances phenotype discovery in asthma EHRs.
Transfer learning aims to faciliate learning tasks in a label-scarce target domain by leveraging knowledge from a related source domain with plenty of labeled data. Often times we may have multiple domains with little or no labeled data as targets waiting to be solved. Most existing efforts tackle target domains separa…
Existing Bayesian models, especially nonparametric Bayesian methods, rely on specially conceived priors to incorporate domain knowledge for discovering improved latent representations. While priors can affect posterior distributions through Bayes' rule, imposing posterior regularization is arguably more direct and in s…
Researchers identify latent variables and causal structures from nonlinear hierarchical models.
A new model for latent class analysis with weighted responses.
Natural image statistics exhibit hierarchical dependencies across multiple scales. Representing such prior knowledge in non-factorial latent tree models can boost performance of image denoising, inpainting, deconvolution or reconstruction substantially, beyond standard factorial "sparse" methodology. We derive a large …
Multitask Gaussian process (MTGP) is powerful for joint learning of multiple tasks with complicated correlation patterns. However, due to the assembling of additive independent latent functions, all current MTGPs including the salient linear model of coregionalization (LMC) and convolution frameworks cannot effectively…
While physics conveys knowledge of nature built from an interplay between observations and theory, it has been considered less importantly in deep neural networks. Especially, there are few works leveraging physics behaviors when the knowledge is given less explicitly. In this work, we propose a novel architecture call…
Generative model for SSc disease trajectories using deep learning.
Unified framework for disentangled VAEs improves latent space interpretability.
Proposes a method to generate realistic counterfactuals by learning relationships.
New spectral clustering method handles discrete covariates for better community detection.