Related papers: On the Theories Behind Hard Negative Sampling for …

Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A…

Signal-background classification is a central problem in High-Energy Physics (HEP), that plays a major role for the discovery of new fundamental particles. A recent method -- the Parametric Neural Network (pNN) -- leverages multiple signal…

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

Attributes, such as metadata and profile, carry useful information which in principle can help improve accuracy in recommender systems. However, existing approaches have difficulty in fully leveraging attribute information due to practical…

In binary classification, there are situations where negative (N) data are too diverse to be fully labeled and we often resort to positive-unlabeled (PU) learning in these scenarios. However, collecting a non-representative N set that…

Deep Neural Networks (DNN) are core components for classification and regression tasks of many software systems. Companies incur in high costs for testing DNN with datasets representative of the inputs expected in operation, as these need…

Most existing image-text matching methods adopt triplet loss as the optimization objective, and choosing a proper negative sample for the triplet of <anchor, positive, negative> is important for effectively training the model, e.g., hard…

Two-sample hypothesis testing for network comparison presents many significant challenges, including: leveraging repeated network observations and known node registration, but without requiring them to operate; relaxing strong structural…

Contrastive learning has been widely studied in sentence representation learning. However, earlier works mainly focus on the construction of positive examples, while in-batch samples are often simply treated as negative examples. This…

The data scarcity of user preferences and the cold-start problem often appear in real-world applications and limit the recommendation accuracy of collaborative filtering strategies. Leveraging the selections of social friends and foes can…

In this paper, we investigate the recommendation task in the most common scenario with implicit feedback (e.g., clicks, purchases). State-of-the-art methods in this direction usually cast the problem as to learn a personalized ranking on a…

Negative sampling is highly effective in handling missing annotations for named entity recognition (NER). One of our contributions is an analysis on how it makes sense through introducing two insightful concepts: missampling and…

Implicit feedback (e.g., clicks, dwell times, etc.) is an abundant source of data in human-interactive systems. While implicit feedback has many advantages (e.g., it is inexpensive to collect, user centric, and timely), its inherent biases…

Compared with the traditional hashing methods, deep hashing methods generate hash codes with rich semantic information and greatly improves the performances in the image retrieval field. However, it is unsatisfied for current deep hashing…

In the case of an imbalance between positive and negative samples, hard negative mining strategies have been shown to help models learn more subtle differences between positive and negative samples, thus improving recognition performance.…

Link prediction is a fundamental task for graph analysis with important applications on the Web, such as social network analysis and recommendation systems, etc. Modern graph link prediction methods often employ a contrastive approach to…

Deep neural networks, when optimized with sufficient data, provide accurate representations of high-dimensional functions; in contrast, function approximation techniques that have predominated in scientific computing do not scale well with…

Riding on the waves of deep neural networks, deep metric learning has also achieved promising results in various tasks using triplet network or Siamese network. Though the basic goal of making images from the same category closer than the…

Bayesian hierarchical models have been demonstrated to provide efficient algorithms for finding sparse solutions to ill-posed inverse problems. The models comprise typically a conditionally Gaussian prior model for the unknown, augmented by…

We consider robust optimization problems, where the goal is to optimize in the worst case over a class of objective functions. We develop a reduction from robust improper optimization to Bayesian optimization: given an oracle that returns…