Related papers: Conditional Imputation for Within-Modality Missing…

Missing data in spatiotemporal systems presents a significant challenge for modern applications, ranging from environmental monitoring to urban traffic management. The integrity of spatiotemporal data often deteriorates due to hardware…

Statistical heterogeneity severely limits the performance of federated learning (FL), motivating several explorations e.g., FedProx, MOON and FedDyn, to alleviate this problem. Despite effectiveness, their considered scenario generally…

Federated learning (FL) is an important paradigm for training global models from decentralized data in a privacy-preserving way. Existing FL methods usually assume the global model can be trained on any participating client. However, in…

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. By encoding a series of cause-effect relations between events,…

In a standard multi-output classification scenario, both features and labels of training data are partially observed. This challenging issue is widely witnessed due to sensor or database failures, crowd-sourcing and noisy communication…

The integration of multimodal data including pathology images and gene profiles is widely applied in precise survival prediction. Despite recent advances in multimodal survival models, collecting complete modalities for multimodal fusion…

A core task in multi-modal learning is to integrate information from multiple feature spaces (e.g., text and audio), offering modality-invariant essential representations of data. Recent research showed that, classical tools such as {\it…

Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade…

Multimodal models integrating natural language and visual information have substantially improved generalization of representation models. However, their effectiveness significantly declines in real-world situations where certain modalities…

Federated learning (FL) enables multiple clients to collaboratively train a global model while keeping local data decentralized. Data heterogeneity (non-IID) across clients has imposed significant challenges to FL, which makes local models…

Multimodal learning often outperforms its unimodal counterparts by exploiting unimodal contributions and cross-modal interactions. However, focusing only on integrating multimodal features into a unified comprehensive representation…

In Federated Learning (FL), multiple clients collaboratively train a model without sharing raw data. This paradigm can be further enhanced by Differential Privacy (DP) to protect local data from information inference attacks and is thus…

Federated Learning (FL) is a distributed machine learning approach that enables devices to collaboratively train models without sharing their local data, ensuring user privacy and scalability. However, applying FL to real-world data…

Existing multimodal sentiment analysis tasks are highly rely on the assumption that the training and test sets are complete multimodal data, while this assumption can be difficult to hold: the multimodal data are often incomplete in…

The imputation of missing values represents a significant obstacle for many real-world data analysis pipelines. Here, we focus on time series data and put forward SSSD, an imputation model that relies on two emerging technologies,…

Cognitive diagnosis model (CDM) is a fundamental and upstream component in intelligent education. It aims to infer students' mastery levels based on historical response logs. However, existing CDMs usually follow the ID-based embedding…

Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systematic biases from…

Federated Learning (FL) enables multiple nodes to collaboratively train a model without sharing raw data. However, FL systems are usually deployed in heterogeneous scenarios, where nodes differ in both data distributions and participation…

Federated Learning (FL) enables distributed optimization without compromising data sovereignty. Yet, where local label distributions are mutually exclusive, standard weight aggregation fails due to conflicting optimization trajectories.…

Finding appropriate low dimensional representations of high-dimensional multi-modal data can be challenging, since each modality embodies unique deformations and interferences. In this paper, we address the problem using manifold learning,…