相关论文: DEUCE: Dual-diversity Enhancement and Uncertainty-…

Sequential recommendation seeks to model the evolution of user interests by capturing temporal user intent and item-level transition patterns. Transformer-based recommenders demonstrate a strong capacity for learning long-range and…

Predicting the performance of highly configurable software systems is the foundation for performance testing and quality assurance. To that end, recent work has been relying on machine/deep learning to model software performance. However, a…

We consider the task of optimally fine-tuning pre-trained multilingual models, given small amounts of unlabelled target data and an annotation budget. In this paper, we introduce DEMUX, a framework that prescribes the exact data-points to…

In this letter, we introduce deep active learning (AL) for multi-label classification (MLC) problems in remote sensing (RS). In particular, we investigate the effectiveness of several AL query functions for MLC of RS images. Unlike the…

Digital data collected over the decades and data currently being produced with use of information technology is vastly the unlabeled data or data without description. The unlabeled data is relatively easy to acquire but expensive to label…

In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these…

Supervised person re-identification (re-id) approaches require a large amount of pairwise manual labeled data, which is not applicable in most real-world scenarios for re-id deployment. On the other hand, unsupervised re-id methods rely on…

Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance and highly heterogeneous clients. We conduct a systematic…

Prompt-based methods leverage the knowledge of pre-trained language models (PLMs) trained with a masked language modeling (MLM) objective; however, these methods are sensitive to template, verbalizer, and few-shot instance selection,…

The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled…

Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty,…

Active learning frameworks offer efficient data annotation without remarkable accuracy degradation. In other words, active learning starts training the model with a small size of labeled data while exploring the space of unlabeled data in…

Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world relevance often exists on a continuum, and recent advances…

Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series,…

Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all…

Active learning (AL) seeks to reduce annotation costs by selecting the most informative samples for labeling, making it particularly valuable in resource-constrained settings. However, traditional evaluation methods, which focus solely on…

Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, we…

Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…

In multi-task learning, labels are often missing irregularly across samples, which can be fully labeled, partially labeled or unlabeled. The irregular label presence often appears in scientific studies due to experimental limitations. It…

Uncertainty estimation is at the core of Active Learning (AL). Most existing methods resort to complex auxiliary models and advanced training fashions to estimate uncertainty for unlabeled data. These models need special design and hence…