Research
On-device research index

arXiv research

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.

169,051 papers · 148 categories

Trend · papers per month

4178341,2511,668 · Jun 202019922001200920172026
48 results for Product Representation Learning

ProductNet curates high-quality product datasets for better product understanding.

problem Lack of high-quality product datasets for product representation learning.
method Curated high-quality product datasets with a multi-modal deep neural network and active learning.
result Master model yields high categorization accuracy (94.7% top-1 accuracy for 1240 classes).

OMBA learns product and user representations for better online market basket analysis.

problem Limited ability to uncover rarely occurring and temporal associations in MBA.
method Jointly learns product and user representations, captures temporal dynamics, scalable online method.
result OMBA outperforms state-of-the-art methods by 21% on real-world datasets.

Convex learning for diverse invariances in semi-inner-product space.

problem Efficiently learning invariant representations for a wide range of invariances.
method Developed a convex representation learning algorithm for generalized invariances modeled as semi-norms, introducing Euclidean embeddings for kernel representers in a semi-inner-product space.
result Accurate invariant representations learned efficiently and effectively, validated by experiments.

Proposes dual product embedding for complementary product representation learning.

problem Detecting complementary relationships from noisy and sparse customer purchase activities.
method Knowledge-aware dual product embedding with multi-task learning and user bias terms.
result Complementary relationships are captured more accurately than simple similarity.

We derive relations between theoretical properties of restricted Boltzmann machines (RBMs), popular machine learning models which form the building blocks of deep learning models, and several natural notions from discrete mathematics and convex geometry. We give implications and equivalences relating RBM-representable …

2012-06-02abs ↗pdf ↗

WIPS optimizes inner product weights to approximate various similarities.

problem Learning high-quality node representations and accurate similarities.
method Weighted inner product similarity (WIPS) with adjustable weights.
result WIPS can approximate arbitrary general similarities including positive definite and indefinite kernels.

A new method for analyzing product competition using low-dimensional embeddings.

problem Computational challenges in studying product-level competition for millions of products.
method Product2Vec, a method based on representation learning algorithm Word2Vec.
result The method produces more accurate demand forecasts and price elasticities compared to state-of-the-art models.

Probabilistic representations, such as Bayesian and Markov networks, are fundamental to much of statistical machine learning. Thus, learning probabilistic representations directly from data is a deep challenge, the main computational bottleneck being inference that is intractable. Tractable learning is a powerful new p…

2019-01-17abs ↗pdf ↗

Complementary products recommendation is an important problem in e-commerce. Such recommendations increase the average order price and the number of products in baskets. Complementary products are typically inferred from basket data. In this study, we propose the BB2vec model. The BB2vec model learns vector representat…

2018-09-25abs ↗pdf ↗

Proposes a comprehensive framework for financial product lead recommendations using graph representation learning and link prediction.

problem Challenges in surface lead recommendations for financial products due to changing market scenarios and difficulty in capturing holder's mindset.
method Bi-partite graph representation of financial holders and funds, GraphSage model for learning representations, link prediction model for ranking recommendations.
result The proposed graph ML solution outperforms baseline by 42%, 22%, and 14% in hit rate for top-k recommendations (50, 100, 200) and 18%, 19%, and 18% on unseen holders.

New model allows sparse graphs with many triangles to be represented.

problem Sparse graphs with many triangles cannot be accurately represented in finite dimensions.
method Infinite-dimensional inner product model with manifold representations.
result Local neighborhoods can be represented in lower dimensions.

Explores tensor products in hyperdimensional computing.

problem Understanding tensor products in hyperdimensional computing.
method Generalized results from graph embeddings to vector symbolic architectures and hyperdimensional computing.
result Tensor product is the most general and expressive representation with errorless unbinding and detection.

Generative Multisensory Network learns 3D scene representations from multiple modalities.

problem Learning robust 3D scene representations from multiple sensory modalities.
method Amortized Product-of-Experts for efficient inference and cross-modal generation.
result The model can infer modality-invariant 3D scene representations efficiently from various sensory modalities.

A new feature coding method for invariant features using tensor products.

problem Learning invariant features for transformations represented by orthogonal matrices.
method Group-invariant feature vector using tensor-product representations of basic representations.
result Group-invariant feature vector contains sufficient discriminative information for linear classifiers.

We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data. This improves symbolic interpretation and systematic generalisation. Our architecture is trained end-to-end through gradient descent on a variety of simple natural language reasoning tasks…

2018-11-29abs ↗pdf ↗

Introduces tensor product for quiver representations and applies to stable bundles and character varieties.

problem Stability and classification of quiver bundles and their subvarieties.
method Definition of tensor product for quiver representations and application to stability and character varieties.
result Tensor products of polystable quiver bundles are polystable and provide insights into character varieties.

We study the semidirect product of a Lie algebra with a representation up to homotopy and provide various examples coming from Courant algebroids, string Lie 2-algebras, and omni-Lie algebroids. In the end, we study the semidirect product of a Lie group with a representation up to homotopy and use it to give an integra…

2009-10-12abs ↗pdf ↗

AI agent predicts industry and product/service codes for companies.

problem Manual curation of company data is expensive and prone to errors.
method Hierarchical multi-class industry code classifier with multi-label product/service code classifier.
result High accuracy (92-96%) achieved with limited labeled data.

Subspace clustering is a useful technique for many computer vision applications in which the intrinsic dimension of high-dimensional data is often smaller than the ambient dimension. Spectral clustering, as one of the main approaches to subspace clustering, often takes on a sparse representation or a low-rank represent…

2018-03-15abs ↗pdf ↗

The paper explores linear representations in language models using counterfactuals.

problem Understanding linear representations and geometric concepts in large language models.
method Formalized linear representation in output and input spaces, identified causal inner product.
result Unified understanding of linear representations and their connection to interpretation and control.

Convolution as inner product has been the founding basis of convolutional neural networks (CNNs) and the key to end-to-end visual representation learning. Benefiting from deeper architectures, recent CNNs have demonstrated increasingly strong representation abilities. Despite such improvement, the increased depth and l…

2017-11-08abs ↗pdf ↗

Friedl and Kim show any taut sutured manifold can be realized as a twisted homology product, but their proof gives no practical description of how complicated the realizing representation needs to be. We give a number of results illustrating the relationship between the topology of a taut sutured handlebody and the com…

2018-10-17abs ↗pdf ↗

This paper introduces a submanifold of the moduli space of unitary representations of the fundamental group of a punctured sphere with fixed local monodromy. The submanifold is defined via products of involutions through Lagrangian subspaces. We show that the moduli space of Lagrangian representations is a Lagrangian s…

2005-06-06abs ↗pdf ↗

Heegaard Floer homology connects to polynomial representations of Hecke algebras.

problem Understanding polynomial representations of double affine Hecke algebras.
method Using higher-dimensional Heegaard Floer homology and topological interpretations.
result Recovery of polynomial representations from Heegaard Floer homology.

Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable. Those properties follow from some conditions (i.e., completeness an…

2017-01-19abs ↗pdf ↗

Unstable minimal surfaces in n-space link to hyperbolic products.

problem Characterizing unstable minimal surfaces in Rn\mathbb{R}^n and their product counterparts.
method Lifting to R\mathbb{R}-trees, deforming to hyperbolic products, and proving instability equivalence.
result Unstable minimal surfaces in Rn\mathbb{R}^n imply unstable surfaces in product hyperbolic spaces.

Study on balanced Hermitian structures on Lie algebras twisted by representations.

problem Conditions for balanced and locally conformally balanced Hermitian structures on Lie algebras.
method Analysis of Hermitian structures on twisted cartesian products of Lie algebras.
result Classification of six-dimensional balanced Hermitian twisted cartesian products Lie algebras.

The application of machine learning techniques to large-scale personalized recommendation problems is a challenging task. Such systems must make sense of enormous amounts of implicit feedback in order to understand user preferences across numerous product categories. This paper presents a deep learning based solution t…

2019-01-11abs ↗pdf ↗

Research decouples Lie algebroids using bicocycle double cross product theory.

problem Understanding decoupling and coupling phenomena in Lie algebroids.
method Bicocycle double cross product realization method.
result Unified product, double cross product, semi-direct product, and cocycle extension frameworks are instances of the general method.

Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation. Unfortunately, learning representations that exhibit invariance …

2018-05-24abs ↗pdf ↗

Elliptical Attention improves transformer performance by focusing on contextually relevant features.

problem Transformer models suffer from representation collapse and are vulnerable to contaminated samples.
method Uses Mahalanobis distance to define hyper-ellipsoidal neighborhoods for attention weights.
result Elliptical Attention reduces representation collapse and enhances model robustness.

New method uses product embeddings to predict bundle success.

problem Designing effective product bundles in large retail settings.
method Leverage historical purchases and clickstream data to generate product embeddings, then use heuristics for complementarity and substitutability.
result Embeddings-based heuristics predict bundle success, robust across categories and retailers.

Proposes using entity embedding vectors to improve Gaussian Process models for knowledge transfer across cell lines.

problem Lack of reuse of experimental data for predicting novel processes.
method Hybrid Gaussian Process models with entity embedding vectors to represent product identity.
result Improved performance in predicting novel processes compared to traditional methods.