Forensic analysts often use social media imagery and texts to understand important events. A primary challenge is the initial sifting of irrelevant posts. This work introduces an interactive process for training an ev...
详细信息
ISBN:
(纸本)9798350364439;9798350364422
Forensic analysts often use social media imagery and texts to understand important events. A primary challenge is the initial sifting of irrelevant posts. This work introduces an interactive process for training an event-centric, learning-based multimodal classification model that automates sanitization. We propose a method based on bayesian graph neural networks (BGNNs) and evaluate active learning and pseudo-labeling formulations to reduce the number of posts the analyst must manually annotate. Our results indicate that BGNNs are useful for social-media data sifting for forensics investigations of events of interest, the value of active learning and pseudo-labeling varies based on the setting, and incorporating unlabelled data from other events improves performance.
Urothelial carcinoma is the most common bladder cancer whose grading is critical to clinical decision-making. The WHO 2004 grading system classifies urothelial carcinoma into either low grade or high grade, but someti...
详细信息
ISBN:
(纸本)9798350313345;9798350313338
Urothelial carcinoma is the most common bladder cancer whose grading is critical to clinical decision-making. The WHO 2004 grading system classifies urothelial carcinoma into either low grade or high grade, but sometimes cases sit on the border between grades. This makes assessment by the pathologist challenging but could potentially lead to under-treatment or over-treatment. The aim of this study was to use deep learning methods to identify and characterise borderline areas in whole slide images (WSIs) from bladder tumour cases. We constructed graphs on WSIs to accelerate computation, where positive unlabeled learning was utilized, accommodating the partial annotation strategy deployed in clinics. We used bayesian deep learning for carcinoma classification, where we modeled the borderline as prediction uncertainty quantified by bayesian graph neural networks. Our experiments showed promising performance of our approach in carcinoma detection and classification, with a potential use case to highlight and better characterise areas on the border for high grade and low grade to pathologists.
Personalized recommender systems are playing an increasingly important role for online consumption platforms. Because of the multitude of relationships existing in recommender systems, graphneuralnetworks (GNNs) bas...
详细信息
ISBN:
(纸本)9781450379984
Personalized recommender systems are playing an increasingly important role for online consumption platforms. Because of the multitude of relationships existing in recommender systems, graphneuralnetworks (GNNs) based approaches have been proposed to better characterize the various relationships between a user and items while modeling a user's preferences. Previous graph-based recommendation approaches process the observed user-item interaction graph as a ground-truth depiction of the relationships between users and items. However, especially in the implicit recommendation setting, all the unobserved user-item interactions are usually assumed to be negative samples. There are missing links that represent a user's future actions. In addition, there may be spurious or misleading positive interactions. To alleviate the above issue, in this work, we take a first step to introduce a principled way to model the uncertainty in the user-item interaction graph using the bayesiangraph Convolutional neural Network framework. We discuss how inference can be performed under our framework and provide a concrete formulation using the bayesian Probabilistic Ranking training loss. We demonstrate the effectiveness of our proposed framework on four benchmark recommendation datasets. The proposed method outperforms state-of-the-art graph-based recommendation models. Furthermore, we conducted an offline evaluation on one industrial large-scale dataset. It shows that our proposed method outperforms the baselines, with the potential gain being more significant for cold-start users. This illustrates the potential practical benefit in real-world recommender systems.
graphneuralnetworks (GNNs) have drawn much attention inessential graph-structured applications. Most prevailing models are founded on the assumption that class distribution within the training set is balanced. Howev...
详细信息
graphneuralnetworks (GNNs) have drawn much attention inessential graph-structured applications. Most prevailing models are founded on the assumption that class distribution within the training set is balanced. However, data collected from real-world scenarios often exhibit long-tailed distributions. Since the loss is dominated by the nodes with majority classes in the objective function of training and the nodes with minority classes have less engagement in the message-passing mechanism, GNN's performance on imbalanced datasets is undoubtedly unsatisfactory. To alleviate above-mentioned issue, this paper focuses on graph imbalance learning from the quantitative and topological perspectives, and correspondingly proposes a novel dynamic self-training with less uncertainty framework, DeLU-BGNN. Specifically, a self-training mechanism combining with a bayesiangraphneural Network is adopted in our DeLU-BGNN framework to assign high confidence pseudo-labels to the nodes with minority classes in the unlabeled set. For solving quantity imbalance, DeLUBGNN augments the nodes with minority classes to the labeled set and dynamically re-balances the class distribution of the training set. For topology imbalance, topology optimization is utilized in DeLU-BGNN to facilitate the propagation of minority nodes during the message-passing process. Extensive experiments conducted on various real-world datasets demonstrate the superiority of our proposed DeLU-BGNN framework in handling the imbalanced node classification problem.
暂无评论