相关论文: Hierarchical Structure Sharing Empowers Multi-task…

Multi-Task Learning (MTL) is a powerful technique that has gained popularity due to its performance improvement over traditional Single-Task Learning (STL). However, MTL is often challenging because there is an exponential number of…

Heterogeneous Graph Neural Networks (HGNNs) are a class of deep learning models designed specifically for heterogeneous graphs, which are graphs that contain different types of nodes and edges. This paper investigates the application of…

MTL is a learning paradigm that effectively leverages both task-specific and shared information to address multiple related tasks simultaneously. In contrast to STL, MTL offers a suite of benefits that enhance both the training process and…

In this paper, we consider a hierarchical distributed multi-task learning (MTL) system where distributed users wish to jointly learn different models orchestrated by a central server with the help of a layer of multiple relays. Since the…

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced…

Multi-Agent Reinforcement Learning is widely used for multi-robot coordination, where simple graphs typically model pairwise interactions. However, such representations fail to capture higher-order collaborations, limiting effectiveness in…

Safety-critical applications such as autonomous driving require robust 3D environment perception algorithms capable of handling diverse and ambiguous surroundings. The predictive performance of classification models is heavily influenced by…

Graph Neural Networks (GNNs) often struggle with heterophilic data, where connected nodes may have dissimilar labels, as they typically assume homophily and rely on local message passing. To address this, we propose creating alternative…

Multi-Task Learning (MTL) is a powerful learning paradigm to improve generalization performance via knowledge sharing. However, existing studies find that MTL could sometimes hurt generalization, especially when two tasks are less…

Node importance estimation problem has been studied conventionally with homogeneous network topology analysis. To deal with network heterogeneity, a few recent methods employ graph neural models to automatically learn diverse sources of…

Graph neural networks (GNNs) often struggle to learn discriminative node representations for heterophilic graphs, where connected nodes tend to have dissimilar labels and feature similarity provides weak structural cues. We propose…

Multi-task learning (MTL) has become an essential machine learning tool for addressing multiple learning tasks simultaneously and has been effectively applied across fields such as healthcare, marketing, and biomedical research. However, to…

With the rapid development of big data and cloud computing, data management has become increasingly challenging. Over the years, a number of frameworks for data management and storage with various characteristics and features have become…

To optimize large Transformer model training, both efficient parallel computing and advanced data management are indispensable. However, current methods often assume a stable and uniform training workload, neglecting data-induced…

Multimedia applications often require concurrent solutions to multiple tasks. These tasks hold clues to each-others solutions, however as these relations can be complex this remains a rarely utilized property. When task relations are…

Node and link churn in multi-party, cross-region clusters over wide-area networks (WANs) often disrupts distributed training. However, checkpoint-based recovery and cloud-centric autoscaling react slowly and assume centralized control,…

Recently, heterogeneous Graph Neural Networks (GNNs) have become a de facto model for analyzing HGs, while most of them rely on a relative large number of labeled data. In this work, we investigate Contrastive Learning (CL), a key component…

Efficient management of on-demand delivery systems is essential for modern urban logistics, especially in densely populated cities with complex spatial layouts. This study introduces a novel, computer-supported cooperative framework that…

Spatial Crowdsourcing (SC) is gaining traction in both academia and industry, with tasks on SC platforms becoming increasingly complex and requiring collaboration among workers with diverse skills. Recent research works address complex…

Designing shared neural architecture plays an important role in multi-task learning. The challenge is that finding an optimal sharing scheme heavily relies on the expert knowledge and is not scalable to a large number of diverse tasks.…