The core of quantitative investment lies in predicting future trends in stock prices. The future trend of a stock is closely related to the industry it belongs to and its relationship with other stocks. Although some ...
详细信息
With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. However, an early diagnosis is not an easy task because it is hard to find...
详细信息
Multi-instance partial-label learning (MIPL) is a paradigm where each training example is encapsulated as a multi-instance bag associated with the candidate label set, which includes one true label and several false p...
Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications. While recent advances in Large Language Models have demonstrated promising capabilities in temporal reasoning, e...
详细信息
Multi-label classification aims to assign a set of proper labels for each instance,where distance metric learning can help improve the generalization ability of instance-based multi-label classification *** multi-labe...
详细信息
Multi-label classification aims to assign a set of proper labels for each instance,where distance metric learning can help improve the generalization ability of instance-based multi-label classification *** multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature *** this paper,a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label *** one hand,compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on com-ponent *** the other hand,compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label *** to the compositional nature of employed distance metric,the resulting problem admits quadratic programming formulation with linear optimization complexity *** number of training *** also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional *** experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification.
Although deep neural networks have achieved remarkable success, they often exhibit a significant deficiency in reliable uncertainty calibration. This paper focus on model calibratability, which assesses how amenable a...
Although deep neural networks have achieved remarkable success, they often exhibit a significant deficiency in reliable uncertainty calibration. This paper focus on model calibratability, which assesses how amenable a model is to be well recalibrated post-hoc. We find that the widely used weight decay regularizer detrimentally affects model calibratability, subsequently leading to a decline in final calibration performance after post-hoc calibration. To identify the underlying causes leading to poor calibratability, we delve into the calibratability of intermediate features across the hidden layers. We observe a U-shaped trend in the calibratability of intermediate features from the bottom to the top layers, which indicates that over-compression of the top representation layers significantly hinders model calibratability. Based on the observations, this paper introduces a weak classifier hypothesis, i.e., given a weak classification head that has not been over-trained, the representation module can be better learned to produce more calibratable features. Consequently, we propose a progressively layer-peeled training (PLP) method to exploit this hypothesis, thereby enhancing model calibratability. Our comparative experiments show the effectiveness of our method, which improves model calibration and also yields competitive predictive performance.
Semi-supervised learning (SSL) is a classical machine learning paradigm dealing with labeled and unlabeled data. However, it often suffers performance degradation in real-world open-set scenarios, where unlabeled data...
Semi-supervised learning (SSL) is a classical machine learning paradigm dealing with labeled and unlabeled data. However, it often suffers performance degradation in real-world open-set scenarios, where unlabeled data contains outliers from novel categories that do not appear in labeled data. Existing studies commonly tackle this challenging open-set SSL problem with detect-and-filter strategy, which attempts to purify unlabeled data by detecting and filtering outliers. In this paper, we propose a novel binary decomposition strategy, which refrains from error-prone procedure of outlier detection by directly transforming the original open-set SSL problem into a number of standard binary SSL problems. Accordingly, a concise yet effective approach named BDMatch is presented. BDMatch confronts two attendant issues brought by binary decomposition, i.e. class-imbalance and representation-compromise, with adaptive logit adjustment and label-specific feature learning respectively. Comprehensive experiments on diversified benchmarks clearly validate the superiority of BDMatch as well as the effectiveness of our binary decomposition strategy.
This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL). Addressing the challenge of limited labeled data, RankMatch effectively utilizes a small number of label...
详细信息
Multi-instance partial-label learning (MIPL) tackles scenarios where each training sample is represented as a multiinstance bag associated with a candidate label set. This set contains one true label and several false...
详细信息
ISBN:
(数字)9798331506681
ISBN:
(纸本)9798331506698
Multi-instance partial-label learning (MIPL) tackles scenarios where each training sample is represented as a multiinstance bag associated with a candidate label set. This set contains one true label and several false positives. Existing MIPL algorithms have predominantly focused on mapping multiinstance bags to candidate label sets for disambiguation. However, these algorithms may not be adequately generalizable in intricate real-world situations due to their reliance on heuristic methods for identifying true labels. In this paper, we propose PROMIPL, i.e., a PRObabilistic generative model for Multi-instance partiallabel learning, to address these challenges. PROMIPL is the first attempt to explore the probabilistic generative model to infer latent ground-truth labeling information from the data generation process in multi-instance partial-label learning. Besides, the discovered underlying structures also provide improved explanations of the classification predictions. To circumvent the computationally intensive process of training the generative model, we formulate a unified variational lower bound within the stochastic gradient variational Bayesian framework for the model parameters. Experimental results from benchmark and realworld datasets show that our proposed PROMIPL is competitive or superior to the state-of-the-art methods.
The UAVs' deployment decision and task computation offloading decision in the UAV-assisted edge computing network significantly impact the operating efficiency of edge network. On the basis of this, the Optimizati...
The UAVs' deployment decision and task computation offloading decision in the UAV-assisted edge computing network significantly impact the operating efficiency of edge network. On the basis of this, the Optimization Model for UAV Cluster Deployment and Computation Offloading Decision (OMUCDCOD) is established. The model jointly optimizes the number, location of UAV s, and task computation offloading decision. Different from previous studies, this model regards the terminal devices in the edge network as virtual MEC servers, and introduces the collaborative computing mode. The task computation offloading decision made can effectively utilize the computing capabilities offered by the edge network. Considering that the two problems of UAV deployment decision and task computation offloading decision are intricately interconnected, we propose a two-layer optimization algorithm combining K-Means and ant colony algorithm (ToKmAc) to solve OMUCDCOD. ToKmAc is divided into upper and lower layers to solve this optimization problem. The upper layer uses K-Means to solve the UAV deployment decision, that is, the number and location of UAVS; the lower layer employs ant colony algorithm to solve computation offloading decision. Finally, extensive experiments verify the effectiveness of OMUCDCOD and ToKmAc.
暂无评论