Information loss
View article
Visualizing the Loss Landscape of Neural Nets Open
Neural network training relies on our ability to find good minimizers of highly non-convex loss functions. It is well known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and we…
View article
Handling Information Loss of Graph Neural Networks for Session-based Recommendation Open
Recently, graph neural networks (GNNs) have gained increasing popularity due to their convincing performance in various applications. Many previous studies also attempted to apply GNNs to session-based recommendation and obtained promising…
View article
Information loss Open
The complete gravitational collapse of a body in general relativity will result in the formation of a black hole. Although the black hole is classically stable, quantum particle creation processes will result in the emission of Hawking rad…
View article
Can Cross Entropy Loss Be Robust to Label Noise? Open
Trained with the standard cross entropy loss, deep neural networks can achieve great performance on correctly labeled data. However, if the training data is corrupted with label noise, deep models tend to overfit the noisy labels, thereby …
View article
Normalized Loss Functions for Deep Learning with Noisy Labels Open
Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross Entropy (CE) loss is not robust to noisy labels. Whilst new l…
View article
Quantifying Differential Privacy under Temporal Correlations Open
Differential Privacy (DP) has received increasing attention as a rigorous privacy framework. Many existing studies employ traditional DP mechanisms (e.g., the Laplace mechanism) as primitives, which assume that the data are independent, or…
View article
A Review of Anonymization for Healthcare Data Open
Mining health data can lead to faster medical decisions, improvement in the quality of treatment, disease prevention, and reduced cost, and it drives innovative solutions within the healthcare sector. However, health data are highly sensit…
View article
Improved Natural Language Generation via Loss Truncation Open
Neural language models are usually trained to match the distributional properties of large-scale corpora by minimizing the log loss. While straightforward to optimize, this approach forces the model to reproduce all variations in the datas…
View article
Nonparadoxical loss of information in black hole evaporation in a quantum collapse model Open
We consider a novel approach to address the black hole information paradox\n(BHIP). The idea is based on adapting, to the situation at hand, the modified\nversions of quantum theory involving spontaneous stochastic dynamical collapse\nof q…
View article
Improving Cross-lingual Entity Alignment via Optimal Transport Open
Cross-lingual entity alignment identifies entity pairs that share the same meanings but locate in different language knowledge graphs (KGs). The study in this paper is to address two limitations that widely exist in current solutions: 1) t…
View article
Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback Open
We introduce and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions and observes some subset of the associated losses. This setting naturally models several situatio…
View article
A New Method of Privacy Protection: Random k-Anonymous Open
A new k-anonymous method which is different from traditional k-anonymous was proposed to solve the problem of privacy protection. Specifically, numerical data achieves k-anonymous by adding noises, and categorical data achieves k-anonymous…
View article
A Comparative Study of Deep Learning Loss Functions for Multi-Label\n Remote Sensing Image Classification Open
This paper analyzes and compares different deep learning loss functions in\nthe framework of multi-label remote sensing (RS) image scene classification\nproblems. We consider seven loss functions: 1) cross-entropy loss; 2) focal\nloss; 3) …
View article
Predicting Users' Motivations behind Location Check-Ins and Utility Implications of Privacy Protection Mechanisms Open
Location check-ins contain both geographical and semantic information about the visited venues, in the form of tags (e.g., ârestaurantâ). Such data might reveal some personal information about users beyond what they actually want to di…
View article
Robust prediction of clinical outcomes using cytometry data Open
Motivation Flow cytometry and mass cytometry are widely used to diagnose diseases and to predict clinical outcomes. When associating clinical features with cytometry data, traditional analysis methods require cell gating as an intermediate…
View article
Improving MMD-GAN Training with Repulsive Loss Function Open
Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum m…
View article
Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion Open
Deep neural networks need large amounts of labeled data to achieve good performance. In real-world applications, labels are usually collected from non-experts such as crowdsourcing to save cost and thus are noisy. In the past few years, de…
View article
Heralded quantum steering over a high-loss channel Open
Entanglement swapping enables verified nonlocal correlations over a high-loss channel with the detection loophole closed.
View article
The cost of quality: Implementing generalization and suppression for anonymizing biomedical data with minimal information loss Open
Our work shows that implementing syntactic privacy models is challenging and that existing algorithms are not well suited for anonymizing data with transformation models which are more complex than generalization alone. As such models have…
View article
Privacy-preserving data publishing for multiple numerical sensitive attributes Open
Anonymized data publication has received considerable attention from the research community in recent years. For numerical sensitive attributes, most of the existing privacy-preserving data publishing techniques concentrate on microdata wi…
View article
Fast and exact search for the partition with minimal information loss Open
In analysis of multi-component complex systems, such as neural systems, identifying groups of units that share similar functionality will aid understanding of the underlying structures of the system. To find such a grouping, it is useful t…
View article
Loss Aversion Reflects Information Accumulation, Not Bias: A Drift-Diffusion Model Study Open
Defined as increased sensitivity to losses, loss aversion is often conceptualized as a cognitive bias. However, findings that loss aversion has an attentional or emotional regulation component suggest that it may instead reflect difference…
View article
Accuracy of weight loss information in Spanish search engine results on the internet Open
Objective To systematically assess the quality of online information related to weight loss that Spanish speakers in the U.S. are likely to access. Methods This study evaluated the accessibility and quality of information for websites that…
View article
Pan-Sharpening Based on CNN+ Pyramid Transformer by Using No-Reference Loss Open
The majority of existing deep learning pan-sharpening methods often use simulated degraded reference data due to the missing of real fusion labels which affects the fusion performance. The normally used convolutional neural network (CNN) c…
View article
Learning from Noisy Labels with Complementary Loss Functions Open
Recent researches reveal that deep neural networks are sensitive to label noises hence leading to poor generalization performance in some tasks. Although different robust loss functions have been proposed to remedy this issue, they suffer …
View article
An Improved Boundary-Aware Perceptual Loss for Building Extraction from VHR Images Open
With the development of deep learning technology, an enormous number of convolutional neural network (CNN) models have been proposed to address the challenging building extraction task from very high-resolution (VHR) remote sensing images.…
View article
Decision-making based on probabilistic linguistic term sets without loss of information Open
Probabilistic linguistic term set (PLTS) provides a much more effective model to compute with words and to express the uncertainty in the pervasive natural language by probability information. In this paper, to avoid loss of information, w…
View article
Multiple Attention Mechanism Enhanced YOLOX for Remote Sensing Object Detection Open
The object detection technologies of remote sensing are widely used in various fields, such as environmental monitoring, geological disaster investigation, urban planning, and military defense. However, the detection algorithms lack the ro…
View article
IDEA: A utility-enhanced approach to incomplete data stream anonymization Open
The prevalence of missing values in the data streams collected in real environments makes them impossible to ignore in the privacy preservation of data streams. However, the development of most privacy preservation methods does not conside…
View article
Efficient search for informational cores in complex systems: Application to brain networks Open
An important step in understanding the nature of the brain is to identify "cores" in the brain network, where brain areas strongly interact with each other. Cores can be considered as essential sub-networks for brain functions. In the last…