Related papers: Identity-Free Deferral For Unseen Experts

The rapid expansion of varied network systems, including the Internet of Things (IoT) and Industrial Internet of Things (IIoT), has led to an increasing range of cyber threats. Ensuring robust protection against these threats necessitates…

Deploying complex machine learning models on resource-constrained devices is challenging due to limited computational power, memory, and model retrainability. To address these limitations, a hybrid system can be established by augmenting…

Recently, data heterogeneity among the training datasets on the local clients (a.k.a., Non-IID data) has attracted intense interest in Federated Learning (FL), and many personalized federated learning methods have been proposed to handle…

International Classification of Diseases(ICD) is an authoritative health care classification system of different diseases and conditions for clinical and management purposes. Considering the complicated and dedicated process to assign…

Personalized learner modeling using cognitive diagnosis (CD), which aims to model learners' cognitive states by diagnosing learner traits from behavioral data, is a fundamental yet significant task in many web learning services. Existing…

Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT devices, to learn a shared model for prediction, while keeping the training data local. This decentralized approach to train models provides…

Face personalization aims to insert specific faces, taken from images, into pretrained text-to-image diffusion models. However, it is still challenging for previous methods to preserve both the identity similarity and editability due to…

Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system's ease of use, and gain users' trust. A typical approach to realize it is natural language…

Modern applications increasingly require unsupervised learning of latent dynamics from high-dimensional time-series. This presents a significant challenge of identifiability: many abstract latent representations may reconstruct…

Advanced diffusion-based Text-to-Image (T2I) models, such as the Stable Diffusion Model, have made significant progress in generating diverse and high-quality images using text prompts alone. However, when non-famous users require…

Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures. It's common that only a few features, called the influential features, meaningfully define the clusters.…

A major challenge in DeepFake forgery detection is that state-of-the-art algorithms are mostly trained to detect a specific fake method. As a result, these approaches show poor generalization across different types of facial manipulations,…

As artificial intelligence (AI) systems play an increasingly prominent role in human decision-making, challenges surface in the realm of human-AI interactions. One challenge arises from the suboptimal AI policies due to the inadequate…

The Two-Stage Learning-to-Defer (L2D) framework has been extensively studied for classification and, more recently, regression tasks. However, many real-world applications require solving both tasks jointly in a multi-task setting. We…

A fundamental feature of human intelligence is the ability to infer high-level abstractions from low-level sensory data. An essential component of such inference is the ability to discover modularized generative mechanisms. Despite many…

Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied…

We introduce implicit Deep Adaptive Design (iDAD), a new method for performing adaptive experiments in real-time with implicit models. iDAD amortizes the cost of Bayesian optimal experimental design (BOED) by learning a design policy…

Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair. This significantly limits their scalability and usability in…

With the rapid development of generative models and multimodal content editing technologies, the key challenge faced by synthetic image detection (SID) lies in cross-distribution generalization to unknown generation sources. In recent…

The proliferation of edge devices has brought Federated Learning (FL) to the forefront as a promising paradigm for decentralized and collaborative model training while preserving the privacy of clients' data. However, FL struggles with a…