Related papers: Trust-Based Social Learning for Communication (TSL…

Reinforcement learning has achieved great success in various applications. To learn an effective policy for the agent, it usually requires a huge amount of data by interacting with the environment, which could be computational costly and…

Collaborative machine learning is challenged by training-time adversarial behaviors. Existing approaches to tolerate such behaviors either rely on a central server or induce high communication costs. We propose Robust Pull-based Epidemic…

Text-to-Speech (TTS) synthesis using deep learning relies on voice quality. Modern TTS models are advanced, but they need large amount of data. Given the growing computational complexity of these models and the scarcity of large,…

Reinforcement learning algorithms often suffer from poor sample efficiency, making them challenging to apply in multi-task or continual learning settings. Efficiency can be improved by transferring knowledge from a previously trained…

Modern approaches to text to speech require the entire input character sequence to be processed before any audio is synthesised. This latency limits the suitability of such models for time-sensitive tasks like simultaneous interpretation.…

In this work, we focus on the communication aspect of decentralized learning, which involves multiple agents training a shared machine learning model using decentralized stochastic gradient descent (D-SGD) over distributed data. In…

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…

Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…

With increasing urban traffic complexity, Traffic Signal Control (TSC) is essential for optimizing traffic flow and improving road safety. Large Language Models (LLMs) emerge as promising approaches for TSC. However, they are prone to…

How do people acquire rich, flexible knowledge about their environment from others despite limited cognitive capacity? Humans are often thought to rely on computationally costly mentalizing, such as inferring others' beliefs. In contrast,…

Generative AI is increasingly embedded in collaborative learning, yet little is known about how AI personas shape learner agency when AI teammates are present but not disclosed. This mechanism study examines how supportive and contrarian AI…

In the recent shift towards human-centric AI, the need for machines to accurately use natural language has become increasingly important. While a common approach to achieve this is to train large language models, this method presents a form…

Federated learning (FL) enables multiple clients to collaboratively train a shared model without disclosing their local datasets. This is achieved by exchanging local model updates with the help of a parameter server (PS). However, due to…

Effective communication is an important skill for enabling information exchange and cooperation in multi-agent settings. Indeed, emergent communication is now a vibrant field of research, with common settings involving discrete cheap-talk…

We describe federated reconnaissance, a class of learning problems in which distributed clients learn new concepts independently and communicate that knowledge efficiently. In particular, we propose an evaluation framework and…

Federated Learning (FL) is a recent model training paradigm in which client devices collaboratively train a model without ever aggregating their data. Crucially, this scheme offers users potential privacy and security benefits by only ever…

Social learning is a key component of human and animal intelligence. By taking cues from the behavior of experts in their environment, social learners can acquire sophisticated behavior and rapidly adapt to new circumstances. This paper…

Federated Learning is a machine learning setting where the goal is to train a high-quality centralized model while training data remains distributed over a large number of clients each with unreliable and relatively slow network…

Communication structure plays a key role in the learning capability of decentralized systems. Structural self-adaptation, by means of self-organization, changes the order as well as the input information of the agents' collective…

Embedding learning has found widespread applications in recommendation systems and natural language modeling, among other domains. To learn quality embeddings efficiently, adaptive learning rate algorithms have demonstrated superior…