arXiv research

Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increa…

We propose a novel learning framework to answer questions such as "if a user is purchasing a shirt, what other items will (s)he need with the shirt?" Our framework learns distributed representations for items from available textual data, with the learned representations representing items in a latent space expressing f…

Collecting labeled data is costly and thus a critical bottleneck in real-world classification tasks. To mitigate this problem, we propose a novel setting, namely learning from complementary labels for multi-class classification. A complementary label specifies a class that a pattern does not belong to. Collecting compl…

Clarinet uses complementary labels to train classifiers with less source data.

Paper proposes a method to adapt classifiers using complementary labels instead of true labels.

A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However, the existing complementary-label learning methods cannot learn from the easily …

We show that any self-complementary graph with $n$ vertices contains a $K_{\lfloor \frac{n+1}{2}\rfloor}$ minor. We derive topological properties of self-complementary graphs.

In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that observations do \textbf{not} belong to. Let $Y$ and $\bar{Y}$ be the true and complementary labels, respectively. We first model the annotati…

Framework transfers complementary operating conditions to train anomaly detectors.

Proposes a method for multi-view clustering that integrates consistent and complementary graph regularizers.

Modern deep learning-based recommendation systems exploit hundreds to thousands of different categorical features, each with millions of different categories ranging from clicks to posts. To respect the natural diversity within the categorical data, embeddings map each category to a unique dense representation within a…

Learning product representations that reflect complementary relationship plays a central role in e-commerce recommender system. In the absence of the product relationships graph, which existing methods rely on, there is a need to detect the complementary relationships directly from noisy and sparse customer purchase ac…

In this note we study the Seifert rational homology spheres with two complementary legs, i.e. with a pair of invariants whose fractions add up to one. We give a complete classification of the Seifert manifolds with 3 exceptional fibers and two complementary legs which bound rational homology balls. The result translate…

Bayesian Complementary Kernelized Learning models complex spatiotemporal data.

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…

A supervised learning framework has been proposed for the situation where each training data is provided with a complementary label that represents a class to which the pattern does not belong. In the existing literature, complementary-label learning has been studied independently from ordinary-label learning, which as…

We establish a form of the h-principle for the existence of foliations quasi-complementary to a given one; the same methods also provide a proof of the classical Mather-Thurston theorem.

Feature selection has attracted significant attention in data mining and machine learning in the past decades. Many existing feature selection methods eliminate redundancy by measuring pairwise inter-correlation of features, whereas the complementariness of features and higher inter-correlation among more than two feat…

UREs lead to overfitting in complex models, especially in complementary label learning.

In contrast to the standard classification paradigm where the true class is given to each training pattern, complementary-label learning only uses training patterns each equipped with a complementary label, which only specifies one of the classes that the pattern does not belong to. The goal of this paper is to derive …

CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.

Deep learning predicts contagion dynamics on complex networks.

Study cryptocurrency price dynamics using adaptive EMD and spectral analysis.

Machine learning and statistical modeling complement each other in healthcare analytics.

This paper studies an environment of simultaneous, separate, first-price auctions for complementary goods. Agents observe private values of each good before making bids, and the complementarity between goods is explicitly incorporated in their utility. For simplicity, a model is presented with two first-price auctions …

Study shows Seifert fibered spaces don't bound rational homology balls.

Paper connects two portfolio methods, HRP and Minimum Variance, revealing their underlying similarity.

New method uses SHapley Additive Explanations to identify anomaly detectors with complementary behaviors.

Paper improves volatility forecasting for new issues and spin-offs.

Sketching accelerates structured prediction methods for large datasets.

Theorem converse to Jordan's curve theorem says that {\it if a compact set $K$ has two complementary domains in $R^{2}$, from each of which it is at every point accessible, it is a simple closed curve}. We show that the requirement of this theorem that {\it all} points of $K$ were accessible from {\it both} complementa…

New framework evaluates model explanations based on decision task improvement.

We obtain integral formulas for a metric-affine space equipped with two complementary orthogonal distributions. The integrand depends on the Ricci and mixed scalar curvatures and invariants of the second fundamental forms and integrability tensors of the distributions. The formulas under some conditions yield splitting…

Paper shows any link can be diagrammed with only triangles and quadrilaterals.

Study compares unsupervised and weakly-supervised methods for anomaly detection at the LHC.

An increasing sequence of integers is said to be universal for knots and links if every knot and link has a projection to the sphere such that the number of edges of each complementary face of the projection comes from the given sequence. This paper is an investigation into which sequences, either finite or infinite, a…

The paper proves integral formulas for manifolds with multiple orthogonal distributions.

Algorithm solves two-sided matching markets with unknown preferences and constraints.

In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN, which aims to jointly optimize model components by incorporating three players, ge…

We use the idea of expressing a nonoriented link as a sum of all oriented links corresponding to the link to present a short proof of the Lickorish-Millett-Turaev formula for the Kauffman polynomial at $z= -a- a^{-1}$. Our approach explains the observation made by Lickorish and Millett that the formula is the generatin…

Combining self-training and contrastive learning improves performance under distribution shift.

This paper investigates two feature-scoring criteria that make use of estimated class probabilities: one method proposed by \citet{shen} and a complementary approach proposed below. We develop a theoretical framework to analyze each criterion and show that both estimate the spread (across all values of a given feature)…

We exhibit the first example of a knot in the three-sphere with a pair of minimal genus Seifert surfaces that can be distinguished using the sutured Floer homology of their complementary manifolds together with the Spin^c-grading. This answers a question of Juhász. More precisely, we show that the Euler characteristic …

We give a complementary generalization of the extensions of Bonnet-Myers theorem obtained by Calabi and also Cheeger-Gromov-Taylor.

We study positive definite quaternionic contact $(4n+3)$-manifolds ($qc$-manifold for short). Just like the $CR$-structure contains the class of Sasaki manifolds, the $qc$-structure admits a class of $3$-Sasaki manifolds with integrable distribution isomorphic to $\mathfrak{su}(2)$. A big difference concerning the inte…

Unified algorithm for minimizing composite functions with flexible design.

Researchers derived Kauffman bracket polynomial for Celtic link shadows using two methods.

Bipartite Riemann-Finsler geometries with complementary Finsler structures are constructed. Calculable examples are presented based on a bilinear-form coefficient for explicit Lorentz violation.