Publications

Revisiting Mixout: An Overlooked Path to Robust Finetuning
Masih Aminbeidokhti
Heitor Rapela Medeiros
Eric Granger
Marco Pedersoli
Finetuning vision foundation models often improves in-domain accuracy but comes at the cost of robustness under distribution shift. We revis… (voir plus)it Mixout, a stochastic regularizer that intermittently replaces finetuned weights with their pretrained reference, through the lens of a single-run, weight-sharing implicit ensemble. This perspective reveals three key levers that govern robustness: the \emph{masking anchor}, \emph{resampling frequency}, and \emph{mask sparsity}. Guided by this analysis, we introduce GMixout, which (i) replaces the fixed anchor with an exponential moving-average snapshot that adapts during training, and (ii) regulates masking period via an explicit resampling-frequency hyperparameter. Our sparse-kernel implementation updates only a small fraction of parameters with no inference-time overhead, enabling training on consumer-grade GPUs. Experiments on benchmarks covering covariate shift, corruption, and class imbalance, ImageNet / ImageNet-LT, DomainNet, iWildCam, and CIFAR100-C, GMixout consistently improves in-domain accuracy beyond zero-shot performance while surpassing both Model Soups and strong parameter-efficient finetuning baselines under distribution shift.
2025-10-08
ArXiv (prépublication)
arxiv.org
arxiv.org
TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
Jacob Chmura
Shenyang Huang
Tran Gia Bao Ngo
Ali Parviz
Farimah Poursafaei
Jure Leskovec
Michael M. Bronstein
Guillaume Rabusseau
Matthias Fey
Reihaneh Rabbany
Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like Py… (voir plus)Torch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175x speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study. TGM is available at https://github.com/tgm-team/tgm
2025-10-08
ArXiv (prépublication)
arxiv.org
arxiv.org
TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
Jacob Chmura
Shenyang Huang
Tran Gia Bao Ngo
Ali Parviz
Farimah Poursafaei
Jure Leskovec
Michael M. Bronstein
Guillaume Rabusseau
Matthias Fey
Reihaneh Rabbany
Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like Py… (voir plus)Torch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175x speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study. TGM is available at https://github.com/tgm-team/tgm
2025-10-08
ArXiv (prépublication)
arxiv.org
arxiv.org
TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
Jacob Chmura
Shenyang Huang
Tran Gia Bao Ngo
Ali Parviz
Farimah Poursafaei
Jure Leskovec
Michael M. Bronstein
Guillaume Rabusseau
Matthias Fey
Reihaneh Rabbany
Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like Py… (voir plus)Torch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175x speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study. TGM is available at https://github.com/tgm-team/tgm
2025-10-08
ArXiv (prépublication)
arxiv.org
arxiv.org
The Markovian Thinker
Milad Aghajohari
Kamran Chitsaz
Amirhossein Kazemnejad
Sarath Chandar
Alessandro Sordoni
Aaron Courville
Siva Reddy
Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Y… (voir plus)et the standard RL"thinking environment", where the state is the prompt plus all prior reasoning tokens, makes the state unbounded and forces attention-based policies to pay quadratic compute as thoughts lengthen. We revisit the environment itself. We propose Markovian Thinking, a paradigm in which the policy advances reasoning while conditioning on a constant-size state, decoupling thinking length from context size. As an immediate consequence this yields linear compute with constant memory. We instantiate this idea with Delethink, an RL environment that structures reasoning into fixed-size chunks. Within each chunk, the model thinks as usual; at the boundary, the environment resets the context and reinitializes the prompt with a short carryover. Through RL, the policy learns to write a textual state near the end of each chunk sufficient for seamless continuation of reasoning after reset. Trained in this environment, an R1-Distill 1.5B model reasons in 8K-token chunks yet thinks up to 24K tokens, matching or surpassing LongCoT-RL trained with a 24K budget. With test-time scaling, Delethink continues to improve where LongCoT plateaus. The effect of linear compute is substantial: we empirically estimate at 96K average thinking length LongCoT-RL costs 27 H100-months vs. 7 for Delethink. Analysis at RL initialization shows off-the-shelf reasoning models (1.5B-120B) often sample Markovian traces zero-shot across diverse benchmarks, providing positive samples that make RL effective at scale. Our results show that redesigning the thinking environment is a powerful lever: it enables very long reasoning without quadratic overhead and opens a path toward efficient, scalable reasoning LLMs.
2025-10-08
ArXiv (prépublication)
arxiv.org
arxiv.org
The Markovian Thinker
Milad Aghajohari
Kamran Chitsaz
Amirhossein Kazemnejad
Sarath Chandar
Alessandro Sordoni
Aaron Courville
Siva Reddy
Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Y… (voir plus)et the standard RL"thinking environment", where the state is the prompt plus all prior reasoning tokens, makes the state unbounded and forces attention-based policies to pay quadratic compute as thoughts lengthen. We revisit the environment itself. We propose Markovian Thinking, a paradigm in which the policy advances reasoning while conditioning on a constant-size state, decoupling thinking length from context size. As an immediate consequence this yields linear compute with constant memory. We instantiate this idea with Delethink, an RL environment that structures reasoning into fixed-size chunks. Within each chunk, the model thinks as usual; at the boundary, the environment resets the context and reinitializes the prompt with a short carryover. Through RL, the policy learns to write a textual state near the end of each chunk sufficient for seamless continuation of reasoning after reset. Trained in this environment, an R1-Distill 1.5B model reasons in 8K-token chunks yet thinks up to 24K tokens, matching or surpassing LongCoT-RL trained with a 24K budget. With test-time scaling, Delethink continues to improve where LongCoT plateaus. The effect of linear compute is substantial: we empirically estimate at 96K average thinking length LongCoT-RL costs 27 H100-months vs. 7 for Delethink. Analysis at RL initialization shows off-the-shelf reasoning models (1.5B-120B) often sample Markovian traces zero-shot across diverse benchmarks, providing positive samples that make RL effective at scale. Our results show that redesigning the thinking environment is a powerful lever: it enables very long reasoning without quadratic overhead and opens a path toward efficient, scalable reasoning LLMs.
2025-10-08
ArXiv (prépublication)
arxiv.org
arxiv.org
Differentially Private Clustered Federated Learning
Saber Malekmohammadi
Afaf Taïk
Golnoosh Farnadi
Federated learning (FL), which is a decentralized machine learning (ML) approach, often incorporates differential privacy (DP) to provide ri… (voir plus)gorous data privacy guarantees to clients. Previous works attempted to address high structured data heterogeneity in vanilla FL settings through clustering clients (a.k.a clustered FL), but these methods remain sensitive and prone to errors, further exacerbated by the DP noise. This vulnerability makes the previous methods inappropriate for differentially private FL (DPFL) under structured data heterogeneity. To address this gap, we propose an algorithm for differentially private clustered FL, which is robust to the DP noise in the system and identifies the underlying clients’ clusters correctly. To this end, we propose to cluster clients based on both their model updates and training loss values. Furthermore, for clustering clients’ model updates at the end of the first round, our proposed approach addresses the server’s uncertainties by employing large batch sizes as well as Gaussian Mixture Models (GMM) to reduce the impact of DP and stochastic noise and avoid potential clustering errors. We provide theoretical analysis to justify our approach and evaluate it across diverse data distributions and privacy budgets. Our experimental results show the approach’s effectiveness in addressing high structured data heterogeneity in DPFL.
2025-10-07
TMLR (accepté)
openreview.net
openreview.net
Differentially Private Clustered Federated Learning
Saber Malekmohammadi
Afaf Taïk
Golnoosh Farnadi
Federated learning (FL), which is a decentralized machine learning (ML) approach, often incorporates differential privacy (DP) to provide ri… (voir plus)gorous data privacy guarantees. Previous works attempted to address high structured data heterogeneity in vanilla FL settings through clustering clients (a.k.a clustered FL), but these methods remain sensitive and prone to errors, further exacerbated by the DP noise. This vulnerability makes the previous methods inappropriate for differentially private FL (DPFL) settings with structured data heterogeneity. To address this gap, we propose an algorithm for differentially private clustered FL, which is robust to the DP noise in the system and identifies the underlying clients' clusters correctly. To this end, we propose to cluster clients based on both their model updates and training loss values. Furthermore, for clustering clients' model updates at the end of the first round, our proposed approach addresses the server's uncertainties by employing large batch sizes as well as Gaussian Mixture Models (GMM) to reduce the impact of DP and stochastic noise and avoid potential clustering errors. This idea is efficient especially in privacy-sensitive scenarios with more DP noise. We provide theoretical analysis to justify our approach and evaluate it across diverse data distributions and privacy budgets. Our experimental results show its effectiveness in addressing large structured data heterogeneity in DPFL.
2025-10-07
TMLR (accepté)
openreview.net
openreview.net
Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
Luca Scimeca
Thomas Jiralerspong
Berton Earnshaw
Jason Hartford
Yoshua Bengio
2025-10-07
ArXiv (prépublication)
arxiv.org
arxiv.org
Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
Luca Scimeca
Thomas Jiralerspong
Berton Earnshaw
Jason Hartford
Yoshua Bengio
Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In th… (voir plus)is work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. We introduce an anisotropic noise operator that shapes these biases by replacing the isotropic forward covariance with a structured, frequency-diagonal covariance. This operator unifies band-pass masks and power-law weightings, allowing us to emphasize or suppress designated frequency bands, while keeping the forward process Gaussian. We refer to this as spectrally anisotropic Gaussian diffusion (SAGD). In this work, we derive the score relation for anisotropic covariances and show that, under full support, the learned score converges to the true data score as
2025-10-07
ArXiv (prépublication)
arxiv.org
arxiv.org
Long Range Navigator (LRN): Extending robot planning horizons beyond metric maps
Matt Schmittle
Rohan Baijal
Nathan Hatch
Rosario Scalise
Mateo Guaman Castro
Sidharth Talia
Khimya Khetarpal
Byron Boots
Siddhartha Srinivasa
A robot navigating an outdoor environment with no prior knowledge of the space must rely on its local sensing, which is in the form of a loc… (voir plus)al metric map or local policy with some fixed horizon. A limited planning horizon can often result in myopic decisions leading the robot off course or worse, into very difficult terrain. In this work, we make a key observation that long range navigation only necessitates identifying good frontier directions for planning instead of full map knowledge. To address this, we introduce Long Range Navigator (LRN), which learns to predict affordable’ frontier directions from high-dimensional camera images. LRN is trained entirely on unlabeled egocentric videos, making it scalable and adaptable. In off-road tests on Spot and a large vehicle, LRN reduces human interventions and improves decision speed when integrated into existing navigation stacks.
2025-10-07
Proceedings of The 8th Conference on Robot Learning (publié)
proceedings.mlr.press
RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
Pranav Atreya
Karl Pertsch
Tony Lee
Moo Jin Kim
Arhan Jain
Artur Kuramshin
Cyrus Neary
Edward S. Hu
Kanav Arora
Kirsty Ellis
Luca Macesanu
Matthew Leonard
Meedeum Cho
Özgür Aslan
Shivin Dass
Tony Wang
Xingfang Yuan
Abhishek Gupta
Dinesh Jayaraman
Glen Berseth … (voir 6 de plus)
Kostas Daniilidis
Roberto Martín-Martín
Youngwoon Lee
Percy Liang
Chelsea Finn
Sergey Levine
Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benc… (voir plus)hmarking typically rely on heavy standardization, either by specifying fixed evaluation tasks and environments, or by hosting centralized "robot challenges", and do not readily scale to evaluating generalist policies across a broad range of tasks and environments. In this work, we propose RoboArena, a new approach for scalable evaluation of generalist robot policies in the real world. Instead of standardizing evaluations around fixed tasks, environments, or locations, we propose to crowd-source evaluations across a distributed network of evaluators. Importantly, evaluators can freely choose the tasks and environments they evaluate on, enabling easy scaling of diversity, but they are required to perform double-blind evaluations over pairs of policies. Then, by aggregating preference feedback from pairwise comparisons across diverse tasks and environments, we can derive a ranking of policies. We instantiate our approach across a network of evaluators at seven academic institutions using the DROID robot platform. Through more than 600 pairwise real-robot evaluation episodes across seven generalist policies, we demonstrate that our crowd-sourced approach can more accurately rank the performance of existing generalist policies than conventional, centralized evaluation approaches, while being more scalable, resilient, and trustworthy. We open our evaluation network to the community and hope that it can enable more accessible comparisons of generalist robot policies.
2025-10-07
Proceedings of The 8th Conference on Robot Learning (publié)
proceedings.mlr.press