Related papers: MAPL: Model Agnostic Peer-to-peer Learning

Personalized Federated Learning (PFL) aims to address the statistical heterogeneity of data across clients by learning the personalized model for each client. Among various PFL approaches, the personalized aggregation-based approach…

While existing alignment paradigms have been integral in developing large language models (LLMs), LLMs often learn an averaged human preference and struggle to model diverse preferences across cultures, demographics, and communities. We…

Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article,…

As AI becomes more personal, e.g., Agentic AI, there is an increasing need for personalizing models for various use cases. Personalized federated learning (PFL) enables each client to collaboratively leverage other clients' knowledge for…

Personalized Federated Learning (PFL) which collaboratively trains a federated model while considering local clients under privacy constraints has attracted much attention. Despite its popularity, it has been observed that existing PFL…

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate…

Centralized recommender systems encounter privacy leakage due to the need to collect user behavior and other private data. Hence, federated recommender systems (FedRec) have become a promising approach with an aggregated global model on the…

In real-world federated learning scenarios, participants could have their own personalized labels which are incompatible with those from other clients, due to using different label permutations or tackling completely different tasks or…

Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous,…

This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning, to bring together the best of both worlds. In particular, it focuses simultaneous learning of multiple…

Social media bot detection is increasingly crucial with the rise of social media platforms. Existing methods predominantly construct social networks as graph and utilize graph neural networks (GNNs) for bot detection. However, most of these…

A fundamental problem in modern supervised learning is computing reliable conditional prediction intervals in high-dimensional settings: existing methods often rely on restrictive modelling assumptions, do not scale as predictor dimension…

Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations,…

We present P2PL, a practical multi-device peer-to-peer deep learning algorithm that, unlike the federated learning paradigm, does not require coordination from edge servers or the cloud. This makes P2PL well-suited for the sheer scale of…

Model merging acquires general capabilities without extra data or training by combining multiple models' parameters. Previous approaches achieve linear mode connectivity by aligning parameters into the same loss basin using permutation…

[Context] Machine learning (ML)-enabled systems are present in our society, driving significant digital transformations. The dynamic nature of ML development, characterized by experimental cycles and rapid changes in data, poses challenges…

Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific…

Graph neural networks (GNNs) excel on homophilic graphs where connected nodes share labels, but struggle with heterophilic graphs where edges do not imply similarity. Moreover, iterative message passing limits scalability due to…

Graph contrastive learning (GCL) has recently emerged as a new concept which allows for capitalizing on the strengths of graph neural networks (GNNs) to learn rich representations in a wide variety of applications which involve abundant…

We consider a collaborative learning scenario in which multiple data-owners wish to jointly train a logistic regression model, while keeping their individual datasets private from the other parties. We propose COPML, a fully-decentralized…