arXiv subjects

Varuna De Silva

Publications and source records attributed to Varuna De Silva.

At least 19 recordsLinked to original sources

arXiv2026

Robust and Efficient Communication for Multi-Agent Learning

Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated messages are both informative and robust to physical constraints remains a significant challenge. This paper introduces Multi-Agent Regularized Communication (MARC), a novel framework inspired by information-theoretic principles of conditional mutual information. MARC employs an attention-based architecture coupled with a unique message regularization mechanism designed to minimize uncertainty regarding future system states, thereby inducing the learning of highly representative communication protocols. Crucially, we evaluate MARC under stringent communication bottlenecks and lossy channels, simulating the real-world constraints of autonomous robotic networks and decentralized systems. Our results demonstrate that MARC significantly outperforms state-of-the-art methods in complex cooperative domains. Furthermore, we provide a deep analysis of message characteristics, proving that MARC maintains high operational performance even under significant data compression, offering a scalable path for deploying intelligent agents in resource-constrained environments.

cs.LG↗

arXiv2026

Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent Modeling

Machine learning can be crucial to help scale complex signal processing applications in scenarios such as healthcare. However, these machine learning models need rich datasets to be trained and there are often cases where it is not possible to access representative datasets. In this paper, we propose a deep generative model based on conditional variational autoencoders with the objective of augmenting the vital signs of healthy individuals in a way that mimics the patterns of a certain clinical condition. More specifically, we use a publicly available ICU (Intensive Care Unit) dataset to train our model and then evaluate it using the vital data that we have collected from healthy individuals. Our results demonstrate that the proposed model can not only learn the underlying dynamics of the ICU data but, more importantly, can reshape our collected data from healthy individuals in a way that is aligned with the vital signs of a certain clinical condition. We propose a distance metric that shows how our model can generate samples that are more aligned with the intended clinical labels when compared to the tested baselines.

cs.LG↗

arXiv2026

Beyond Peak TOPS/W: A System-Level Perspective on Hybrid Digital, Analogue and Neuromorphic Computing

The digital revolution, which progressively replaced analogue methods with digital circuits, has entered a new phase as AI expands across cloud infrastructure, mobile networks, wearables and physical systems, including drones and robots. Digital computing remains the general-purpose foundation of this expansion: it supports heterogeneous, on-device and decentralised AI through programmable control, mature software and decades of accumulated engineering infrastructure. Yet as energy and data-movement constraints become more significant, that same foundation is increasingly being extended rather than replaced by selected analogue and physical principles that it can host, configure and verify. Photonic, in-memory and neuromorphic architectures offer routes to reducing data movement and accelerating matrix-intensive and event-driven processing, not as alternatives to digital infrastructure but as specialised engines operating within it. This paper argues that hybrid digital--analogue computing represents a credible pathway towards more energy-efficient AI systems: one in which physical substrates earn an expanding role only where they deliver a measurable system-level advantage, under digital orchestration that manages integration, uncertainty and fallback. It examines the architectural principles, workload suitability, energy accounting, software requirements, limitations and open challenges associated with this transition, and argues that future progress should be evaluated through deployed-system metrics rather than isolated peak tera operations per second per watt (TOPS/W) claims.

cs.AR↗

arXiv2026

ATRACT: A Trustworthy Robotic Autonomous system to support Casualty Triage

At a time when drones are increasingly associated with hostile operations, we re-purpose them for humanitarian and life-saving applications. However, adapting search and rescue drones for battlefield triage remains extremely challenging; the technology must perform reliably to support frontline medics who are forced to operate under extreme uncertainty, restricted access, and significant personal risk. Due to growing vulnerabilities of casualty evacuation in conflicting zones, this paper presents ATRACT (A Trustworthy Robotic Autonomous system to support Casualty Triage), a novel human-in-the-loop decision support system to enable early battlefield triage during the critical post-trauma period. ATRACT integrates drone-captured video with wearable sensor input for multi-modal learning to support casualty-state assessment, thereby addressing the limitations of existing systems. Drone video captures fine-grained behavioural cues, such as pose, posture, while body-worn sensors provide complementary physiological signals, including heart rate, breathing rate, and movement. By combining two modalities, ATRACT provides evidence to support the early judgement of medics when direct access to the casualty is delayed, risky, or restricted. To mitigate the data realism gap pertaining to injured actions, a conditional variational autoencoder is devised for data augmentation. Experimental results on our drone captured dataset show that proposed pipeline achieves 85.7% accuracy for action classification; while our lightweight CNN visual encoder remains competitive with stronger pre-trained video backbones. Overall, the results support ATRACT as a practically meaningful step towards remote triage in contested environments, where multi-modal sensing, human oversight and trustworthy decision support can improve casualty prioritisation, and lessen the exposure of frontline medics.

cs.HC↗

arXiv2026

QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation

Federated Learning (FL) enables privacy-preserving intelligence on Internet of Things (IoT) devices but incurs a significant carbon footprint due to the high energy cost of frequent uplink transmission. While pre-trained models are increasingly available on edge devices, their potential to reduce the energy overhead of fine-tuning remains underexplored. In this work, we propose QuantFL, a sustainable FL framework that leverages pre-trained initialisation to enable aggressive, computationally lightweight quantisation. We demonstrate that pre-training naturally concentrates update statistics, allowing us to use memory-efficient bucket quantisation without the energy-intensive overhead of complex error-feedback mechanisms. On MNIST and CIFAR-100, QuantFL reduces total communication by 40\% ($\simeq40\%$ total-bit reduction with full-precision downlink; $\geq80\%$ on uplink or when downlink is quantised) while matching or exceeding uncompressed baselines under strict bandwidth budgets; BU attains 89.00\% (MNIST) and 66.89\% (CIFAR-100) test accuracy with orders of magnitude fewer bits. We also account for uplink and downlink costs and provide ablations on quantisation levels and initialisation. QuantFL delivers a practical, "green" recipe for scalable training on battery-constrained IoT networks.

cs.LG↗

arXiv2025

DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation

Federated Learning (FL) enables decentralized model training without sharing raw data, offering strong privacy guarantees. However, existing FL protocols struggle to defend against Byzantine participants, maintain model utility under non-independent and identically distributed (non-IID) data, and remain lightweight for edge devices. Prior work either assumes trusted hardware, uses expensive cryptographic tools, or fails to address privacy and robustness simultaneously. We propose DSFL, a Dual-Server Byzantine-Resilient Federated Learning framework that addresses these limitations using a group-based secure aggregation approach. Unlike LSFL, which assumes non-colluding semi-honest servers, DSFL removes this dependency by revealing a key vulnerability: privacy leakage through client-server collusion. DSFL introduces three key innovations: (1) a dual-server secure aggregation protocol that protects updates without encryption or key exchange, (2) a group-wise credit-based filtering mechanism to isolate Byzantine clients based on deviation scores, and (3) a dynamic reward-penalty system for enforcing fair participation. DSFL is evaluated on MNIST, CIFAR-10, and CIFAR-100 under up to 30 percent Byzantine participants in both IID and non-IID settings. It consistently outperforms existing baselines, including LSFL, homomorphic encryption methods, and differential privacy approaches. For example, DSFL achieves 97.15 percent accuracy on CIFAR-10 and 68.60 percent on CIFAR-100, while FedAvg drops to 9.39 percent under similar threats. DSFL remains lightweight, requiring only 55.9 ms runtime and 1088 KB communication per round.

cs.CR↗

arXiv2025

PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification

Large Language Models (LLMs) excel in text classification, but their complexity hinders interpretability, making it difficult to understand the reasoning behind their predictions. Explainable AI (XAI) methods like LIME and SHAP offer local explanations by identifying influential words, but they rely on computationally expensive perturbations. These methods typically generate thousands of perturbed sentences and perform inferences on each, incurring a substantial computational burden, especially with LLMs. To address this, we propose \underline{P}erturbation-free \underline{L}ocal \underline{Ex}planation (PLEX), a novel method that leverages the contextual embeddings extracted from the LLM and a ``Siamese network" style neural network trained to align with feature importance scores. This one-off training eliminates the need for subsequent perturbations, enabling efficient explanations for any new sentence. We demonstrate PLEX's effectiveness on four different classification tasks (sentiment, fake news, fake COVID-19 news and depression), showing more than 92\% agreement with LIME and SHAP. Our evaluation using a ``stress test" reveals that PLEX accurately identifies influential words, leading to a similar decline in classification accuracy as observed with LIME and SHAP when these words are removed. Notably, in some cases, PLEX demonstrates superior performance in capturing the impact of key features. PLEX dramatically accelerates explanation, reducing time and computational overhead by two and four orders of magnitude, respectively. This work offers a promising solution for explainable LLM-based text classification.

cs.CL↗

arXiv2024

Fully Independent Communication in Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning (MARL) comprises a broad area of research within the field of multi-agent systems. Several recent works have focused specifically on the study of communication approaches in MARL. While multiple communication methods have been proposed, these might still be too complex and not easily transferable to more practical contexts. One of the reasons for that is due to the use of the famous parameter sharing trick. In this paper, we investigate how independent learners in MARL that do not share parameters can communicate. We demonstrate that this setting might incur into some problems, to which we propose a new learning scheme as a solution. Our results show that, despite the challenges, independent agents can still learn communication strategies following our method. Additionally, we use this method to investigate how communication in MARL is affected by different network capacities, both for sharing and not sharing parameters. We observe that communication may not always be needed and that the chosen agent network sizes need to be considered when used together with communication in order to achieve efficient learning.

cs.LG↗

arXiv2024

Player Pressure Map -- A Novel Representation of Pressure in Soccer for Evaluating Player Performance in Different Game Contexts

In soccer, contextual player performance metrics are invaluable to coaches. For example, the ability to perform under pressure during matches distinguishes the elite from the average. Appropriate pressure metric enables teams to assess players' performance accurately under pressure and design targeted training scenarios to address their weaknesses. The primary objective of this paper is to leverage both tracking and event data and game footage to capture the pressure experienced by the possession team in a soccer game scene. We propose a player pressure map to represent a given game scene, which lowers the dimension of raw data and still contains rich contextual information. Not only does it serve as an effective tool for visualizing and evaluating the pressure on the team and each individual, but it can also be utilized as a backbone for accessing players' performance. Overall, our model provides coaches and analysts with a deeper understanding of players' performance under pressure so that they make data-oriented tactical decisions.

cs.LG↗

arXiv2023

Learning Independently from Causality in Multi-Agent Environments

Multi-Agent Reinforcement Learning (MARL) comprises an area of growing interest in the field of machine learning. Despite notable advances, there are still problems that require investigation. The lazy agent pathology is a famous problem in MARL that denotes the event when some of the agents in a MARL team do not contribute to the common goal, letting the teammates do all the work. In this work, we aim to investigate this problem from a causality-based perspective. We intend to create the bridge between the fields of MARL and causality and argue about the usefulness of this link. We study a fully decentralised MARL setup where agents need to learn cooperation strategies and show that there is a causal relation between individual observations and the team reward. The experiments carried show how this relation can be used to improve independent agents in MARL, resulting not only on better performances as a team but also on the rise of more intelligent behaviours on individual agents.

cs.LG↗

arXiv2023

Staged Reinforcement Learning for Complex Tasks through Decomposed Environments

Reinforcement Learning (RL) is an area of growing interest in the field of artificial intelligence due to its many notable applications in diverse fields. Particularly within the context of intelligent vehicle control, RL has made impressive progress. However, currently it is still in simulated controlled environments where RL can achieve its full super-human potential. Although how to apply simulation experience in real scenarios has been studied, how to approximate simulated problems to the real dynamic problems is still a challenge. In this paper, we discuss two methods that approximate RL problems to real problems. In the context of traffic junction simulations, we demonstrate that, if we can decompose a complex task into multiple sub-tasks, solving these tasks first can be advantageous to help minimising possible occurrences of catastrophic events in the complex task. From a multi-agent perspective, we introduce a training structuring mechanism that exploits the use of experience learned under the popular paradigm called Centralised Training Decentralised Execution (CTDE). This experience can then be leveraged in fully decentralised settings that are conceptually closer to real settings, where agents often do not have access to a central oracle and must be treated as isolated independent units. The results show that the proposed approaches improve agents performance in complex tasks related to traffic junctions, minimising potential safety-critical problems that might happen in these scenarios. Although still in simulation, the investigated situations are conceptually closer to real scenarios and thus, with these results, we intend to motivate further research in the subject.

cs.LG↗

arXiv2023

Passing Heatmap Prediction Based on Transformer Model and Tracking Data

Although the data-driven analysis of football players' performance has been developed for years, most research only focuses on the on-ball event including shots and passes, while the off-ball movement remains a little-explored area in this domain. Players' contributions to the whole match are evaluated unfairly, those who have more chances to score goals earn more credit than others, while the indirect and unnoticeable impact that comes from continuous movement has been ignored. This research presents a novel deep-learning network architecture which is capable to predict the potential end location of passes and how players' movement before the pass affects the final outcome. Once analysed more than 28,000 pass events, a robust prediction can be achieved with more than 0.7 Top-1 accuracy. And based on the prediction, a better understanding of the pitch control and pass option could be reached to measure players' off-ball movement contribution to defensive performance. Moreover, this model could provide football analysts a better tool and metric to understand how players' movement over time contributes to the game strategy and final victory.

cs.LG↗

arXiv2023

Embedding Contextual Information through Reward Shaping in Multi-Agent Learning: A Case Study from Google Football

Artificial Intelligence has been used to help human complete difficult tasks in complicated environments by providing optimized strategies for decision-making or replacing the manual labour. In environments including multiple agents, such as football, the most common methods to train agents are Imitation Learning and Multi-Agent Reinforcement Learning (MARL). However, the agents trained by Imitation Learning cannot outperform the expert demonstrator, which makes humans hardly get new insights from the learnt policy. Besides, MARL is prone to the credit assignment problem. In environments with sparse reward signal, this method can be inefficient. The objective of our research is to create a novel reward shaping method by embedding contextual information in reward function to solve the aforementioned challenges. We demonstrate this in the Google Research Football (GRF) environment. We quantify the contextual information extracted from game state observation and use this quantification together with original sparse reward to create the shaped reward. The experiment results in the GRF environment prove that our reward shaping method is a useful addition to state-of-the-art MARL algorithms for training agents in environments with sparse reward signal.

cs.LG↗

arXiv2023

Discovering Causality for Efficient Cooperation in Multi-Agent Environments

In cooperative Multi-Agent Reinforcement Learning (MARL) agents are required to learn behaviours as a team to achieve a common goal. However, while learning a task, some agents may end up learning sub-optimal policies, not contributing to the objective of the team. Such agents are called lazy agents due to their non-cooperative behaviours that may arise from failing to understand whether they caused the rewards. As a consequence, we observe that the emergence of cooperative behaviours is not necessarily a byproduct of being able to solve a task as a team. In this paper, we investigate the applications of causality in MARL and how it can be applied in MARL to penalise these lazy agents. We observe that causality estimations can be used to improve the credit assignment to the agents and show how it can be leveraged to improve independent learning in MARL. Furthermore, we investigate how Amortized Causal Discovery can be used to automate causality detection within MARL environments. The results demonstrate that causality relations between individual observations and the team reward can be used to detect and punish lazy agents, making them develop more intelligent behaviours. This results in improvements not only in the overall performances of the team but also in their individual capabilities. In addition, results show that Amortized Causal Discovery can be used efficiently to find causal relations in MARL.

cs.AI↗

arXiv2023

Causality Detection for Efficient Multi-Agent Reinforcement Learning

When learning a task as a team, some agents in Multi-Agent Reinforcement Learning (MARL) may fail to understand their true impact in the performance of the team. Such agents end up learning sub-optimal policies, demonstrating undesired lazy behaviours. To investigate this problem, we start by formalising the use of temporal causality applied to MARL problems. We then show how causality can be used to penalise such lazy agents and improve their behaviours. By understanding how their local observations are causally related to the team reward, each agent in the team can adjust their individual credit based on whether they helped to cause the reward or not. We show empirically that using causality estimations in MARL improves not only the holistic performance of the team, but also the individual capabilities of each agent. We observe that the improvements are consistent in a set of different environments.

cs.AI↗

arXiv2023

Deep Generative Multi-Agent Imitation Model as a Computational Benchmark for Evaluating Human Performance in Complex Interactive Tasks: A Case Study in Football

Evaluating the performance of human is a common need across many applications, such as in engineering and sports. When evaluating human performance in completing complex and interactive tasks, the most common way is to use a metric having been proved efficient for that context, or to use subjective measurement techniques. However, this can be an error prone and unreliable process since static metrics cannot capture all the complex contexts associated with such tasks and biases exist in subjective measurement. The objective of our research is to create data-driven AI agents as computational benchmarks to evaluate human performance in solving difficult tasks involving multiple humans and contextual factors. We demonstrate this within the context of football performance analysis. We train a generative model based on Conditional Variational Recurrent Neural Network (VRNN) Model on a large player and ball tracking dataset. The trained model is used to imitate the interactions between two teams and predict the performance from each team. Then the trained Conditional VRNN Model is used as a benchmark to evaluate team performance. The experimental results on Premier League football dataset demonstrates the usefulness of our method to existing state-of-the-art static metric used in football analytics.

stat.ML↗

arXiv2022

Text to Image Synthesis using Stacked Conditional Variational Autoencoders and Conditional Generative Adversarial Networks

Synthesizing a realistic image from textual description is a major challenge in computer vision. Current text to image synthesis approaches falls short of producing a highresolution image that represent a text descriptor. Most existing studies rely either on Generative Adversarial Networks (GANs) or Variational Auto Encoders (VAEs). GANs has the capability to produce sharper images but lacks the diversity of outputs, whereas VAEs are good at producing a diverse range of outputs, but the images generated are often blurred. Taking into account the relative advantages of both GANs and VAEs, we proposed a new stacked Conditional VAE (CVAE) and Conditional GAN (CGAN) network architecture for synthesizing images conditioned on a text description. This study uses Conditional VAEs as an initial generator to produce a high-level sketch of the text descriptor. This high-level sketch output from first stage and a text descriptor is used as an input to the conditional GAN network. The second stage GAN produces a 256x256 high resolution image. The proposed architecture benefits from a conditioning augmentation and a residual block on the Conditional GAN network to achieve the results. Multiple experiments were conducted using CUB and Oxford-102 dataset and the result of the proposed approach is compared against state-ofthe-art techniques such as StackGAN. The experiments illustrate that the proposed method generates a high-resolution image conditioned on text descriptions and yield competitive results based on Inception and Frechet Inception Score using both datasets

cs.CV↗

arXiv2022

Residual Q-Networks for Value Function Factorizing in Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning (MARL) is useful in many problems that require the cooperation and coordination of multiple agents. Learning optimal policies using reinforcement learning in a multi-agent setting can be very difficult as the number of agents increases. Recent solutions such as Value Decomposition Networks (VDN), QMIX, QTRAN and QPLEX adhere to the centralized training and decentralized execution scheme and perform factorization of the joint action-value functions. However, these methods still suffer from increased environmental complexity, and at times fail to converge in a stable manner. We propose a novel concept of Residual Q-Networks (RQNs) for MARL, which learns to transform the individual Q-value trajectories in a way that preserves the Individual-Global-Max criteria (IGM), but is more robust in factorizing action-value functions. The RQN acts as an auxiliary network that accelerates convergence and will become obsolete as the agents reach the training objectives. The performance of the proposed method is compared against several state-of-the-art techniques such as QPLEX, QMIX, QTRAN and VDN, in a range of multi-agent cooperative tasks. The results illustrate that the proposed method, in general, converges faster, with increased stability and shows robust performance in a wider family of environments. The improvements in results are more prominent in environments with severe punishments for non-cooperative behaviours and especially in the absence of complete state information during training time.

cs.LG↗