Related papers: Adaptive Hardness Negative Sampling for Collaborat…
Auxiliary particle filters (APFs) are a class of sequential Monte Carlo (SMC) methods for Bayesian inference in state-space models. In their original derivation, APFs operate in an extended state space using an auxiliary variable to improve…
Monte Carlo methods are often necessary for the implementation of optimal Bayesian estimators. A fundamental technique that can be used to generate samples from virtually any target probability distribution is the so-called rejection…
Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks. The development of Hypergraph Neural Networks (HGNNs) has emerged as a valuable method to manage…
In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance…
Large-scale pre-trained Vision-Language Models (VLMs) have exhibited impressive zero-shot performance and transferability, allowing them to adapt to downstream tasks in a data-efficient manner. However, when only a few labeled samples are…
Markov Chain Monte Carlo (MCMC) methods, such as the Metropolis-Hastings (MH) algorithm, are widely used for Bayesian inference. One of the most important issues for any MCMC method is the convergence of the Markov chain, which depends…
Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence…
Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs is difficult, since the training distribution is dynamic…
In this study, we propose a feature extraction framework based on contrastive learning with adaptive positive and negative samples (CL-FEFA) that is suitable for unsupervised, supervised, and semi-supervised single-view feature extraction.…
Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically stored with…
Conformal inference is a statistical method used to construct prediction sets for point predictors, providing reliable uncertainty quantification with probability guarantees. This method utilizes historical labeled data to estimate the…
Feature selection (FS) is a fundamental challenge in machine learning, particularly for high-dimensional tabular data, where interpretability and computational efficiency are critical. Existing FS methods often cannot automatically detect…
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes.…
Temporal graph neural networks Tgnn have exhibited state-of-art performance in future-link prediction tasks. Training of these TGNNs is enumerated by uniform random sampling based unsupervised loss. During training, in the context of a…
Recommender system (RS) aims to capture personalized preferences from massive user behaviors, making them pivotal in the era of information explosion. However, the presence of ``information cocoons'', interaction sparsity, cold-start…
Graph neural networks (GNNs) have been widely applied in the recommendation tasks and have obtained very appealing performance. However, most GNN-based recommendation methods suffer from the problem of data sparsity in practice. Meanwhile,…
The learn-to-compare paradigm of contrastive representation learning (CRL), which compares positive samples with negative ones for representation learning, has achieved great success in a wide range of domains, including natural language…
Non-active adaptive sampling is a way of building machine learning models from a training data base which are supposed to dynamically and automatically derive guaranteed sample size. In this context and regardless of the strategy used in…
One-class collaborative filtering (OC-CF) is a common class of recommendation problem where only the positive class is explicitly observed (e.g., purchases, clicks). Autoencoder based recommenders such as AutoRec and variants demonstrate…
Learning visual similarity requires to learn relations, typically between triplets of images. Albeit triplet approaches being powerful, their computational complexity mostly limits training to only a subset of all possible training…