Publications (51)
Bures-Wasserstein Flow Matching for Graph Generation
Keyue Jiang, Jiahao Cui, Xiaowen Dong +1
Graph generation has emerged as a critical task in fields ranging from drug discovery to circuit design. Contemporary approaches, notably diffusion and flow-based models, have achi…
Price-based Controller for Quality-Fair HTTP Adaptive Streaming (Extended Version)
Stefano D'Aronco, Laura Toni, Pascal Frossard
HTTP adaptive streaming (HAS) has become the universal technology for video streaming over the Internet. Many HAS system designs aim at sharing the network bandwidth in a rate-fair…
A Survey of Temporal Credit Assignment in Deep Reinforcement Learning
Eduardo Pignatelli, Johan Ferret, Matthieu Geist +4
The Credit Assignment Problem (CAP) refers to the longstanding challenge of Reinforcement Learning (RL) agents to associate actions with their long-term consequences. Solving the C…
MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation
Clement Vignac, Nagham Osman, Laura Toni +1
This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D arrangement of atoms. Unlike existing methods that rely on pre…
Graph signal processing for machine learning: A review and new perspectives
Xiaowen Dong, Dorina Thanou, Laura Toni +2
The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are o…
Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm
Yuheng Bu, Gholamali Aminian, Laura Toni +2
We provide an information-theoretic analysis of the generalization ability of Gibbs-based transfer learning algorithms by focusing on two popular transfer learning approaches, …
Optimal Layered Representation for Adaptive Interactive Multiview Video Streaming
Ana De Abreu, Laura Toni, Nikolaos Thomos +3
We consider an interactive multiview video streaming (IMVS) system where clients select their preferred viewpoint in a given navigation window. To provide high quality IMVS, many h…
LGDC: Latent Graph Diffusion via Spectrum-Preserving Coarsening
Nagham Osman, Keyue Jiang, Davide Buffelli +2
Graph generation is a critical task across scientific domains. Existing methods fall broadly into two categories: autoregressive models, which iteratively expand graphs, and one-sh…
A Markov Random Field model for Hypergraph-based Machine Learning
Bohan Tang, Keyue Jiang, Laura Toni +2
Understanding the data-generating process is essential for building machine learning models that generalise well while ensuring robustness and interpretability. This paper addresse…
Spatio-temporal Graph-RNN for Point Cloud Prediction
Pedro Gomes, Silvia Rossi, Laura Toni
In this paper, we propose an end-to-end learning network to predict future frames in a point cloud sequence. As main novelty, an initial layer learns topological information of poi…
Differentiable Linear Bandit Algorithm
Kaige Yang, Laura Toni
Upper Confidence Bound (UCB) is arguably the most commonly used method for linear multi-arm bandit problems. While conceptually and computationally simple, this method highly relie…
Extending 3-DoF Metrics to Model User Behaviour Similarity in 6-DoF Immersive Applications
Silvia Rossi, Irene Viola, Laura Toni +1
Immersive reality technologies, such as Virtual and Augmented Reality, have ushered a new era of user-centric systems, in which every aspect of the coding--delivery--rendering chai…
Explaining Hierarchical Features in Dynamic Point Cloud Processing
Pedro Gomes, Silvia Rossi, Laura Toni
This paper aims at bringing some light and understanding to the field of deep learning for dynamic point cloud processing. Specifically, we focus on the hierarchical features learn…
An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift
Gholamali Aminian, Mahed Abroshan, Mohammad Mahdi Khalili +2
A common assumption in semi-supervised learning is that the labeled, unlabeled, and test data are drawn from the same distribution. However, this assumption is not satisfied in man…
Information-theoretic Characterizations of Generalization Error for the Gibbs Algorithm
Gholamali Aminian, Yuheng Bu, Laura Toni +2
Various approaches have been developed to upper bound the generalization error of a supervised learning algorithm. However, existing bounds are often loose and even vacuous when ev…
From In Silico to In Vitro: Evaluating Molecule Generative Models for Hit Generation
Nagham Osman, Vittorio Lembo, Giovanni Bottegoni +1
Hit identification is a critical yet resource-intensive step in the drug discovery pipeline, traditionally relying on high-throughput screening of large compound libraries. Despite…
Heterogeneous Graph Structure Learning through the Lens of Data-generating Processes
Keyue Jiang, Bohan Tang, Xiaowen Dong +1
Inferring the graph structure from observed data is a key task in graph machine learning to capture the intrinsic relationship between data entities. While significant advancements…
NAVIX: Scaling MiniGrid Environments with JAX
Eduardo Pignatelli, Jarek Liesen, Robert Tjarko Lange +3
As Deep Reinforcement Learning (Deep RL) research moves towards solving large-scale worlds, efficient environment simulations become crucial for rapid experimentation. However, mos…
Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information
Gholamali Aminian, Yuheng Bu, Laura Toni +2
Bounding the generalization error of a supervised learning algorithm is one of the most important problems in learning theory, and various approaches have been developed. However,…
Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
Eduardo Pignatelli, Johan Ferret, Tim Rockäschel +4
The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory f…
Prioritized Random MAC Optimization via Graph-based Analysis
Laura Toni, Pascal Frossard
Motivated by the analogy between successive interference cancellation and iterative belief-propagation on erasure channels, irregular repetition slotted ALOHA (IRSA) strategies hav…
Finite Length Performance of Random Slotted ALOHA Strategies
Konstantinos Dovelos, Laura Toni, Pascal Frossard
Multiple connected devices sharing common wireless resources might create interference if they access the channel simultaneously. Medium access control (MAC) protocols gener- ally…
Semi-supervised Batch Learning From Logged Data
Gholamali Aminian, Armin Behnamnia, Roberto Vega +5
Off-policy learning methods are intended to learn a policy from logged data, which includes context, action, and feedback (cost or reward) for each sample point. In this work, we b…
Graph-Based Recommendation System
Kaige Yang, Laura Toni
In this work, we study recommendation systems modelled as contextual multi-armed bandit (MAB) problems. We propose a graph-based recommendation system that learns and exploits the…
Laplacian-regularized graph bandits: Algorithms and theoretical analysis
Kaige Yang, Xiaowen Dong, Laura Toni
We consider a stochastic linear bandit problem with multiple users, where the relationship between users is captured by an underlying graph and user preferences are represented as…
Representation Learning on Graphs: A Reinforcement Learning Application
Sephora Madjiheurem, Laura Toni
In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation…
In-Network View Synthesis for Interactive Multiview Video Systems
Laura Toni, Gene Cheung, Pascal Frossard
To enable Interactive multiview video systems with a minimum view-switching delay, multiple camera views are sent to the users, which are used as reference images to synthesize add…
Optimized Packet Scheduling in Multiview Video Navigation Systems
Laura Toni, Thomas Maugey, Pascal Frossard
In multiview video systems, multiple cameras generally acquire the same scene from different perspectives, such that users have the possibility to select their preferred viewpoint.…
Impact of Connectivity on Laplacian Representations in Reinforcement Learning
Tommaso Giorgi, Pierriccardo Olivieri, Keyue Jiang +2
Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL)…
Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning
Aya Kayal, Sattar Vakili, Laura Toni +1
Reinforcement Learning (RL) problems are being considered under increasingly more complex structures. While tabular and linear models have been thoroughly explored, the analytical…
Error Analysis on Graph Laplacian Regularized Estimator
Kaige Yang, Xiaowen Dong, Laura Toni
We provide a theoretical analysis of the representation learning problem aimed at learning the latent variables (design matrix) of observations with the knowledge of the c…
Information-Theoretic Bounds on the Moments of the Generalization Error of Learning Algorithms
Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues
Generalization error bounds are critical to understanding the performance of machine learning models. In this work, building upon a new bound of the expected value of an arbitrary…
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
Aya Kayal, Sattar Vakili, Laura Toni +2
Bayesian optimization (BO) with preference-based feedback has recently garnered significant attention due to its emerging applications. We refer to this problem as Bayesian Optimiz…
Adaptive Streaming in Interactive Multiview Video Systems
Xue Zhang, Laura Toni, Pascal Frossard +2
Multiview applications endow final users with the possibility to freely navigate within 3D scenes with minimum-delay. A real feeling of scene navigation is enabled by transmitting…
AGAR: Attention Graph-RNN for Adaptative Motion Prediction of Point Clouds of Deformable Objects
Pedro Gomes, Silvia Rossi, Laura Toni
This paper focuses on motion prediction for point cloud sequences in the challenging case of deformable 3D objects, such as human body motion. First, we investigate the challenges…
Joint Source, Channel and Space-time Coding of Progressive Sources in MIMO Systems
Meesue Shin, Laura Toni, Sang-Hyo Kim +1
The optimization of joint source and channel coding for a sequence of numerous progressive packets is a challenging problem. Further, the problem becomes more complicated if the sp…
The impact of intrinsic rewards on exploration in Reinforcement Learning
Aya Kayal, Eduardo Pignatelli, Laura Toni
One of the open challenges in Reinforcement Learning is the hard exploration problem in sparse reward environments. Various types of intrinsic rewards have been proposed to address…
Online Network Source Optimization with Graph-Kernel MAB
Laura Toni, Pascal Frossard
We propose Grab-UCB, a graph-kernel multi-arms bandit algorithm to learn online the optimal source placement in large scale networks, such that the reward obtained from a priori un…
Learning Algorithm Generalization Error Bounds via Auxiliary Distributions
Gholamali Aminian, Saeed Masiha, Laura Toni +1
Generalization error bounds are essential for comprehending how well machine learning models work. In this work, we suggest a novel method, i.e., the Auxiliary Distribution Method,…
Optimized Adaptive Streaming Representations based on System Dynamics
Laura Toni, Ramon Aparicio-Pardo, Karine Pires +3
Adaptive streaming addresses the increasing and heterogenous demand of multimedia content over the Internet by offering several encoded versions for each video sequence. Each versi…
Multi-View Video Packet Scheduling
Laura Toni, Thomas Maugey, Pascal Frossard
In multiview applications, multiple cameras acquire the same scene from different viewpoints and generally produce correlated video streams. This results in large amounts of highly…
Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks
Michael Doherty, Alejandra Beghelli, Laura Toni
Reinforcement learning (RL) has been widely applied to dynamic routing, modulation and spectrum assignment (RMSA) in optical networks, yet no prior work has trained a transformer m…
Reinforcement Learning Using known Invariances
Alexandru Cioba, Aya Kayal, Laura Toni +2
In many real-world reinforcement learning (RL) problems, the environment exhibits inherent symmetries that can be exploited to improve learning efficiency. This paper develops a th…
Jensen-Shannon Information Based Characterization of the Generalization Error of Learning Algorithms
Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues
Generalization error bounds are critical to understanding the performance of machine learning models. In this work, we propose a new information-theoretic based generalization erro…
IRSA Transmission Optimization via Online Learning
Laura Toni, Pascal Frossard
In this work, we propose a new learning framework for optimising transmission strategies when irregular repetition slotted ALOHA (IRSA) MAC protocol is considered. We cast the onli…
State2vec: Off-Policy Successor Features Approximators
Sephora Madjiheurem, Laura Toni
A major challenge in reinforcement learning (RL) is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcemen…
The Sum-Rate-Distortion Region of Correlated Gauss-Markov Sources
Giuseppe Cocco, Laura Toni
Efficient low-delay video encoders are of fundamental importance to provide timely feedback in remotely controlled platforms such as drones. In order to fully understand the theore…
Improved Utility-based Congestion Control for Delay-Constrained Communication
Stefano D'Aronco, Laura Toni, Sergio Mena +2
Due to the presence of buffers in the inner network nodes, each congestion event leads to buffer queueing and thus to an increasing end-to-end delay. In the case of delay sensitive…
Spherical clustering of users navigating 360° content
Silvia Rossi, Francesca De Simone, Pascal Frossard +1
In Virtual Reality (VR) applications, understanding how users explore the omnidirectional content is important to optimize content creation, to develop user-centric services, or ev…
Effects of Dropout on Performance in Long-range Graph Learning Tasks
Jasraj Singh, Keyue Jiang, Brooks Paige +1
Message Passing Neural Networks (MPNNs) are a class of Graph Neural Networks (GNNs) that propagate information across the graph via local neighborhoods. The scheme gives rise to tw…
Optimal Representations for Adaptive Streaming in Interactive Multi-View Video Systems
Laura Toni, Pascal Frossard
Interactive multi-view video streaming (IMVS) services permit to remotely immerse within a 3D scene. This is possible by transmitting a set of reference camera views (anchor views)…