We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world relation extraction. GRD aims to identify unlabeled instances in existing pre-defined relations or discover novel relations by ass...
详细信息
Metriplectic systems are learned from data in a way that scales quadratically in both the size of the state and the rank of the metriplectic data. Besides being provably energy conserving and entropy stable, the propo...
Logical reasoning consistently plays a fundamental and significant role in the domains of knowledge engineering and artificial intelligence. Recently, Large Language Models (LLMs) have emerged as a noteworthy innovati...
详细信息
Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video ...
详细信息
Federated Learning (FL) succeeds in collaborative and privacy-preserving ML model training among multiple distributed data owners. To maintain a healthy FL ecosystem, it is crucial to estimate the contributions of all...
详细信息
Efficient integration of renewable power such as wind energy in electricity markets is among the highest priorities. However, the deterministic market designs may not effectively adapt to the uncertainty of renewable ...
Efficient integration of renewable power such as wind energy in electricity markets is among the highest priorities. However, the deterministic market designs may not effectively adapt to the uncertainty of renewable power. In this paper, we investigate a joint energy and frequency regulation market clearing considering wind power uncertainty. By introducing the chance-constrained market design, we propose a joint market-clearing strategy for both conventionally deterministic units and uncertain wind farms. By the simulation based on real market data, we show that as the confidence level increases, system stability improves, but this comes at the expense of increased wind abandonment losses and higher operating costs in the market. Simultaneously, a higher penetration of wind power leads to lower market operating costs and energy shadow prices.
Generalized Category Discovery (GCD) is a crucial real-world task that aims to recognize both known and novel categories from an unlabeled dataset by leveraging another labeled dataset with only known categories. Desp...
详细信息
Generalized Category Discovery (GCD) is a crucial real-world task that aims to recognize both known and novel categories from an unlabeled dataset by leveraging another labeled dataset with only known categories. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge transfer between labeled and unlabeled data and noisy representation learning on the unlabeled data. The former leads to unreliable estimation of learning targets for novel categories and the latter hinders models from learning discriminative features. To mitigate these two issues, we propose a Transfer and Alignment Network (TAN), which incorporates two knowledge transfer mechanisms to calibrate the biased knowledge and two feature alignment mechanisms to learn discriminative features. Specifically, we model different categories with prototypes and transfer the prototypes in labeled data to correct model bias towards known categories. On the one hand, we pull instances with known categories in unlabeled data closer to these prototypes to form more compact clusters and avoid boundary overlap between known and novel categories. On the other hand, we use these prototypes to calibrate noisy prototypes estimated from unlabeled data based on category similarities, which allows for more accurate estimation of prototypes for novel categories that can be used as reliable learning targets later. After knowledge transfer, we further propose two feature alignment mechanisms to acquire both instance- and category-level knowledge from unlabeled data by aligning instance features with both augmented features and the calibrated prototypes, which can boost model performance on both known and novel categories with less noise. Experiments on three benchmark datasets show that our model outperforms SOTA methods, especially on novel categories. Theoretical analysis is provided for an in-depth understanding
Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predicti...
Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled instances are supervised by classifying labeled bags. The MIL-based methods are relatively well studied with cogent performance achieved on classification but not on localization. Generally, they locate temporal regions by the video-level classification but overlook the temporal variations of feature semantics. To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics. Specifically, our model entails two components, the first is an unsupervised change-points detection module that detects change-points by learning the latent representations of video features in a temporal hierarchy based on their rates of change, and the second is an attention-based classification model that selects the change-points of the foreground as the boundaries. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNet-v1.3. The experiments show that our method outperforms current state-of-the-art methods, and even achieves comparable performance with fully-supervised methods.
Logical reasoning task involves diverse types of complex reasoning over text, based on the form of multiple-choice question answering. Given the context, question and a set of options as the input, previous methods ac...
详细信息
Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predicti...
详细信息
暂无评论