相关论文: Adapted tree boosting for Transfer Learning

Transfer learning (TL) utilizes data or knowledge from one or more source domains to facilitate the learning in a target domain. It is particularly useful when the target domain has very few or no labeled data, due to annotation expense,…

While artificial intelligence (AI)-based decision-making systems are increasingly popular, significant concerns on the potential discrimination during the AI decision-making process have been observed. For example, the distribution of…

Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized by querying the target model, or a transfer-based approach…

Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target domain data…

Numerous algorithms have been proposed for transferring knowledge from a label-rich domain (source) to a label-scarce domain (target). Almost all of them are proposed for a closed-set scenario, where the source and the target domain…

Training a good deep learning model requires substantial data and computing resources, which makes the resulting neural model a valuable intellectual property. To prevent the neural network from being undesirably exploited, non-transferable…

Information on standing dead trees is important for understanding forest ecosystem functioning and resilience but has been lacking over large geographic regions. Climate change has caused large-scale tree mortality events that can remain…

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…

Federated learning improves data privacy and efficiency in machine learning performed over networks of distributed devices, such as mobile phones, IoT and wearable devices, etc. Yet models trained with federated learning can still fail to…

Regression prediction plays a crucial role in practical applications and strongly relies on data annotation. However, due to prohibitive annotation costs or domain-specific constraints, labeled data in the target domain is often scarce,…

The use of neural networks has been very successful in a wide variety of applications. However, it has recently been observed that it is difficult to generalize the performance of neural networks under the condition of distributional shift.…

In today's world, with the rise of numerous social platforms, it has become relatively easy for anyone to spread false information and lure people into traps. Fraudulent schemes and traps are growing rapidly in the investment world. Due to…

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object…

Authentication is a task aiming to confirm the truth between data instances and personal identities. Typical authentication applications include face recognition, person re-identification, authentication based on mobile devices and so on.…

Tabular data stands out as one of the most frequently encountered types in high energy physics. Unlike commonly homogeneous data such as pixelated images, simulating high-dimensional tabular data and accurately capturing their correlations…

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

In the faceless world of the Internet,online fraud is one of the greatest reasons of loss for web merchants.Advanced solutions are needed to protect e businesses from the constant problems of fraud.Many popular fraud detection algorithms…

By leveraging data from a fully labeled source domain, unsupervised domain adaptation (UDA) improves classification performance on an unlabeled target domain through explicit discrepancy minimization of data distribution or adversarial…

Predicting the price of used vehicles is a more interesting and needed problem by many users. Vehicle price prediction can be a challenging task due to the high number of attributes that should be considered for accurate prediction. The…

Domain adaptation investigates the problem of leveraging knowledge from a well-labeled source domain to an unlabeled target domain, where the two domains are drawn from different data distributions. Because of the distribution shifts,…