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.
Efficient method for vertex embedding and community detection.
A fast graph embedding method for large graphs.
MCSAE improves speaker embedding by focusing on both high- and low-level features.
Extends graph encoder embedding to weighted graphs and matrices.
The paper introduces a method for detecting principal communities and embedding vertices.
Acoustic Neighbor Embeddings map speech and text to fixed dimensions for phonetic confusability.
New framework infers multiple classes per image for one-shot learning.
Paper explores embedding methods for detecting pseudo-cliques in random graphs, showing limitations and potential.
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols. Despite its simplicity, such approach yields the number of parameters that grows linearly with the vocabulary s…
Embedding methods such as word embedding have become pillars for many applications containing discrete structures. Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying linear transformation based on "one-hot" encoding of the discrete symbols. …
Improved graph embedding through refined linear transformation and community recovery.
Author2Vec generates user embeddings from social media data.
Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutional network generators by inverting a fixed embedding operator. Therefore, they do not require to be o…
A brain can detect outlier just by using only normal samples. Similarly, one-class classification (OCC) also uses only normal samples to train the model and trained model can be used for outlier detection. In this paper, a multi-layer architecture for OCC is proposed by stacking various Graph-Embedded Kernel Ridge Regr…
Transformers encode latent distributions in text, improving performance in out-of-distribution cases.
We construct a series of finitely presented semigroups. The centers of these semigroups encode uniquely up to rigid ambient isotopy in 3-space all non-oriented spatial graphs. This encoding is obtained by using three-page embeddings of graphs into the product of the line with the cone on three points. By exploiting thr…
In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residual network (ResNet) into increasingly fine sub-regions and extract speaker embeddings from each sub-…
A new drug embedding method using hierarchical drug relations and chemical structures.
We describe the (complex) quaternionic geometry encoded by the embeddings of the Riemann sphere, with nonnegative normal bundles.
Enhances graph classification with multiple graphs.
BTZSC benchmarks zero-shot text classification across diverse models.
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…
Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of …
Centroid-Encoder reduces high-dimensional data for better visualization.
AGE improves graph embedding by smoothing features and iteratively enhancing node embeddings.
Capturing sentence semantics plays a vital role in a range of text mining applications. Despite continuous efforts on the development of related datasets and models in the general domain, both datasets and models are limited in biomedical and clinical domains. The BioCreative/OHNLP organizers have made the first attemp…
Paper tackles zero-shot activity recognition using video features and text embeddings.
Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate bias. In natural language processing, gender bias has been shown to exist in contex…
A new method learns node embeddings for signed directed networks by capturing both first-order and high-order topologies.
The paper explores how semantic independence can be captured in text embeddings using partial orthogonality.
Non-linear manifold learning enables high-dimensional data analysis, but requires out-of-sample-extension methods to process new data points. In this paper, we propose a manifold learning algorithm based on deep learning to create an encoder, which maps a high-dimensional dataset and its low-dimensional embedding, and …
When doing representation learning on data that lives on a known non-trivial manifold embedded in high dimensional space, it is natural to desire the encoder to be homeomorphic when restricted to the manifold, so that it is bijective and continuous with a continuous inverse. Using topological arguments, we show that wh…
With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as only a single embedding is learned for every word in the vocabulary, the model fails to optimally re…
Improves latent space structure for better data representation.
We introduce a novel encoder-decoder architecture to embed functional processes into latent vector spaces. This embedding can then be decoded to sample the encoded functions over any arbitrary domain. This autoencoder generalizes the recently introduced Conditional Neural Process (CNP) model of random processes. Our ar…
Acoustic word embeddings --- fixed-dimensional vector representations of arbitrary-length words --- have attracted increasing interest in query-by-example spoken term detection. Recently, on the fact that the orthography of text labels partly reflects the phonetic similarity between the words' pronunciation, a multi-vi…
SELO model predicts link signs better than SDGNN using subgraph encoding and linear optimization.
The success of machine learning methods heavily relies on having an appropriate representation for data at hand. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about data. However, recently there has been a surge in approaches that learn …
FedGTEA learns new tasks in federated learning with task embeddings and alignment.
New model combines neural networks and embeddings for better choice modeling interpretability.
SiamJEPA uses Siamese student encoders to improve JEPA-based representation learning.
New method for Transformer models to encode position information without sequential bias.
New method for embedding large networks without attributes, achieving state-of-the-art performance.
New method for fair influence maximization in social networks.
For a product of interest, we propose a search method to surface a set of reference products. The reference products can be used as candidates to support downstream modeling tasks and business applications. The search method consists of product representation learning and fingerprint-type vector searching. The product …
This paper proposes grid cells encode position via a conformal isometric embedding of 2D physical space.
In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem. FOFE enables us to encode variable-length sequence of words into a theoretically unique fixed-size representation that can be fed into a feed forward neural network (FFNN),…
Quasi-orthonormal encoding reduces high dimensionality for categorical data.