Searcharxiv⌕ Search

arXiv subjects

Cesare Alippi

Publications and source records attributed to Cesare Alippi.

At least 19 recordsLinked to original sources
arXiv2026

Causal Semantic Alignment for LLM-based Time Series Forecasting

Recent advances in Large Language Models (LLMs) have opened new possibilities for time series forecasting by enabling alignment between temporal patterns and pretrained word embeddings. However, most LLM-based methods overlook the heterogeneous nature of time series, where dynamic fluctuations and invariant semantics are entangled. This entanglement introduces spurious correlations during the alignment, as dynamic components act as confounders by simultaneously influencing invariant components and the resulting aligned embeddings. To address this issue, a variable-level alignment framework CVAformer is proposed. CVAformer explicitly disentangles each variable into invariant and dynamic components just before alignment, and applies causal intervention to mitigate the confounding effect of the dynamics. To better support variable-level alignment, CVAformer replaces the standard causal attention in LLMs with a non-causal attention mechanism that captures interactions among variables at each time step. Extensive experiments across long-term, short-term, few-shot, and zero-shot forecasting settings indicate that CVAformer matches or exceeds state-of-the-art performance on most datasets, and in some cases achieves notably better accuracy. Experimental results validate the effectiveness of variable-level alignment and dynamic disentanglement in CVAformer, offering a new perspective for LLM-based time series tasks.

cs.LG↗
arXiv2026

Why Do Time Series Models Need Long Context Windows?

Modern deep learning models for forecasting groups of time series rely on increasingly longer observation windows. However, the benefit of increasing the window size is often simply attributed to capturing long-range dependencies, and broader discussion on how global forecasting models leverage input observations has been limited. In this paper, we show that forecasting groups of time series involves two objectives: (i) generative process identification (GPI), i.e., inferring the specific process generating the input sequence, and (ii) conditional forecasting (CF), i.e., predicting future values given input observations. From this perspective, optimal predictions can be interpreted as an average over plausible data-generating processes, weighted by their likelihood given the input window. This suggests another explanation for the benefits of long context windows: they reduce the uncertainty about which specific process is generating the input time series during operation. We prove that even for processes with memory length $P$, an input window size strictly larger than $P$ is necessary to achieve the minimum attainable error. Finally, we show how decoupling GPI and CF can improve computational scalability without compromising accuracy. Experiments on synthetic and real-world data validate our insights and their relevance for designing forecasting architectures.

cs.LG↗
arXiv2026

SWING: Unlocking Implicit Graph Representations for Graph Random Features

We propose SWING: Space Walks for Implicit Network Graphs, a new class of algorithms for computations involving Graph Random Features on graphs given by implicit representations (i-graphs), where edge-weights are defined as bi-variate functions of feature vectors in the corresponding nodes. Those classes of graphs include several prominent examples, such as: $ε$-neighborhood graphs, used on regular basis in machine learning. Rather than conducting walks on graphs' nodes, those methods rely on walks in continuous spaces, in which those graphs are embedded. To accurately and efficiently approximate original combinatorial calculations, SWING applies customized Gumbel-softmax sampling mechanism with linearized kernels, obtained via random features coupled with importance sampling techniques. This algorithm is of its own interest. SWING relies on the deep connection between implicitly defined graphs and Fourier analysis, presented in this paper. SWING is accelerator-friendly and does not require input graph materialization. We provide detailed analysis of SWING and complement it with thorough experiments on different classes of i-graphs.

cs.LG↗
arXiv2026

Beyond Softmax: A Natural Parameterization for Categorical Random Variables

Latent categorical variables are frequently found in deep learning architectures. They can model actions in discrete reinforcement-learning environments, represent categories in latent-variable models, or express relations in graph neural networks. Despite their widespread use, their discrete nature poses significant challenges to gradient-descent learning algorithms. While a substantial body of work has offered improved gradient estimation techniques, we take a complementary approach. Specifically, we: 1) revisit the ubiquitous $\textit{softmax}$ function and demonstrate its limitations from an information-geometric perspective; 2) replace the $\textit{softmax}$ with the $\textit{catnat}$ function, a function composed of a sequence of hierarchical binary splits; we prove that this choice offers significant advantages to gradient descent due to the resulting diagonal Fisher Information Matrix. A rich set of experiments - including graph structure learning, variational autoencoders, and reinforcement learning - empirically show that the proposed function improves the learning efficiency and yields models characterized by consistently higher test performance. $\textit{Catnat}$ is simple to implement and seamlessly integrates into existing codebases. Moreover, it remains compatible with standard training stabilization techniques and, as such, offers a better alternative to the $\textit{softmax}$ function.

cs.LG↗
arXiv2026

Graph State-Space Models and Latent Relational Inference

State-space models effectively model multivariate time series by updating over time a representation of the system state from which predictions are made. The state representation is usually a vector without any explicit structure. Relational inductive biases, e.g., associated with dependencies among input signals and state representations, are not explicitly exploited during processing, leaving unattended opportunities for effective modeling. The manuscript aims to fill this gap by matching state-space modeling and spatio-temporal data where the relational information, say the functional graph capturing latent dependencies, is learned directly from time series. In particular, we propose Graph State-Space Models, a novel probabilistic framework that jointly learns state-space dynamics and latent relational structures end-to-end on downstream tasks. The proposed framework generalizes several state-of-the-art methods and, as we show, is effective in extracting meaningful latent relational structures and obtaining accurate forecasts.

cs.LG↗
arXiv2026

Assessment of Spatio-Temporal Predictors in the Presence of Missing and Heterogeneous Data

Deep learning methods achieve remarkable predictive performance in modeling complex, large-scale data. However, assessing the quality of derived models has become increasingly challenging, as more classical statistical assumptions may no longer apply. These difficulties are particularly pronounced for spatio-temporal data, which exhibit dependencies across both space and time and are often characterized by nonlinear dynamics, time variance, and missing observations, hence calling for new accuracy assessment methodologies. This paper introduces a residual correlation analysis framework for assessing the optimality of spatio-temporal relational-enabled neural predictive models, notably in settings with incomplete and heterogeneous data. By leveraging the principle that residual correlation indicates information not captured by the model, enabling the identification and localization of regions in space and time where predictive performance can be improved. A strength of the proposed approach is that it operates under minimal assumptions, allowing also for robust evaluation of deep learning models applied to multivariate time series, even in the presence of missing and heterogeneous data. In detail, the methodology constructs tailored spatio-temporal graphs to encode sparse spatial and temporal dependencies and employs asymptotically distribution-free summary statistics to detect time intervals and spatial regions where the model underperforms. The effectiveness of what proposed is demonstrated through experiments on both synthetic and real-world datasets using state-of-the-art predictive models.

stat.ML↗
arXiv2026

TimeOmni-VL: Unified Models for Time Series Understanding and Generation

Recent time series modeling faces a sharp divide between numerical generation and semantic understanding, with research showing that generation models often rely on superficial pattern matching, while understanding-oriented models struggle with high-fidelity numerical output. Although unified multimodal models (UMMs) have bridged this gap in vision, their potential for time series remains untapped. We propose TimeOmni-VL, the first vision-centric framework that unifies time series understanding and generation through two key innovations: (1) Fidelity-preserving bidirectional mapping between time series and images (Bi-TSI), which advances Time Series-to-Image (TS2I) and Image-to-Time Series (I2TS) conversions to ensure near-lossless transformations. (2) Understanding-guided generation. We introduce TSUMM-Suite, a novel dataset consisting of six understanding tasks rooted in time series analytics and coupled with two generation tasks. With a calibrated Chain-of-Thought, TimeOmni-VL is the first to leverage time series understanding as an explicit control signal for high-fidelity generation. Experiments confirm that this unified approach significantly improves semantic understanding and numerical precision, establishing a new frontier for multimodal time series modeling.

cs.LG↗
arXiv2026

PeakWeather: MeteoSwiss Weather Station Measurements for Spatiotemporal Deep Learning

Accurate weather forecasts are essential for supporting a wide range of activities and decision-making processes, as well as mitigating the impacts of adverse weather events. While traditional numerical weather prediction (NWP) remains the cornerstone of operational forecasting, machine learning is emerging as a powerful alternative for fast, flexible, and scalable predictions. We introduce PeakWeather, a high-quality dataset of surface weather observations collected every 10 minutes over more than 8 years from the ground stations of the Federal Office of Meteorology and Climatology MeteoSwiss's measurement network. The dataset includes a diverse set of meteorological variables from 302 station locations distributed across Switzerland's complex topography and is complemented with topographical indices derived from digital height models for context. Ensemble forecasts from the currently operational high-resolution NWP model are provided as a baseline forecast against which to evaluate new approaches. The dataset's richness supports a broad spectrum of spatiotemporal tasks, including time series forecasting at various scales, graph structure learning, imputation, and virtual sensing. As such, PeakWeather serves as a real-world benchmark to advance both foundational machine learning research, meteorology, and sensor-based applications.

cs.LG↗
arXiv2026

Scalable Analytic Classifiers with Associative Drift Compensation for Class-Incremental Learning of Vision Transformers

Class-incremental learning (CIL) with Vision Transformers (ViTs) faces a major computational bottleneck during the classifier reconstruction phase, where most existing methods rely on costly iterative stochastic gradient descent (SGD). We observe that analytic Regularized Gaussian Discriminant Analysis (RGDA) provides a Bayes-optimal alternative with accuracy comparable to SGD-based classifiers; however, its quadratic inference complexity limits its use in large-scale CIL scenarios. To overcome this, we propose Low-Rank Factorized RGDA (LR-RGDA), a scalable classifier that combines RGDA's expressivity with the efficiency of linear classifiers. By exploiting the low-rank structure of the covariance via the Woodbury matrix identity, LR-RGDA decomposes the discriminant function into a global affine term refined by a low-rank quadratic perturbation, reducing the inference complexity from $\mathcal{O}(Cd^2)$ to $\mathcal{O}(d^2 + Crd^2)$, where $C$ is the class number, $d$ the feature dimension, and $r \ll d$ the subspace rank. To mitigate representation drift caused by backbone updates, we further introduce Hopfield-based Distribution Compensator (HopDC), a training-free mechanism that uses modern continuous Hopfield Networks to recalibrate historical class statistics through associative memory dynamics on unlabeled anchors, accompanied by a theoretical bound on the estimation error. Extensive experiments on diverse CIL benchmarks demonstrate that our framework achieves state-of-the-art performance, providing a scalable solution for large-scale class-incremental learning with ViTs. Code: https://github.com/raoxuan98-hash/lr_rgda_hopdc.

cs.CV↗
arXiv2025

Position: Current Benchmarking Hinders Real Progress in Deep Learning for Time Series Forecasting

Deep learning models have grown popular in time series applications. However, the large quantity of newly proposed architectures and the often contradictory empirical results make it difficult to assess which design choice and model component drives performance. In this position paper, we argue that current benchmarking practices fail to identify the factors responsible for performance differences, thus slowing down progress in the field. In particular, differences in crucial design dimensions are overlooked when comparing architectures, ultimately leading to inconsistent outcomes. To support our position, we show that such differences-often treated as mere implementation details-can have a greater impact than adopting specific sequence modeling layers. We discuss how overlooked aspects (such as globality and locality) can (1) fundamentally change the class of the forecasting method and (2) drastically affect empirical results. Our findings suggest rethinking our benchmarking practices and focusing on the foundational aspects of the forecasting problem when designing and comparing architectures. As a concrete step, we propose an auxiliary forecasting model card, i.e., a template with a set of fields to characterize existing and new forecasting architectures based on key design choices.

cs.LG↗
arXiv2025

Online Continual Graph Learning

Continual Learning (CL) aims to incrementally acquire new knowledge while mitigating catastrophic forgetting. Within this setting, Online Continual Learning (OCL) focuses on updating models promptly and incrementally from single or small batches of observations from a data stream. Extending OCL to graph-structured data is crucial, as many real-world networks evolve over time and require timely, online predictions. However, existing continual or streaming graph learning methods typically assume access to entire graph snapshots or multiple passes over tasks, violating the efficiency constraints of the online setting. To address this gap, we introduce the Online Continual Graph Learning (OCGL) setting, which formalizes node-level continual learning on evolving graphs under strict memory and computational budgets. OCGL defines how a model incrementally processes a stream of node-level information while maintaining anytime inference and respecting resource constraints. We further establish a comprehensive benchmark comprising seven datasets and nine CL strategies, suitably adapted to the OCGL setting, enabling a standardized evaluation setup. Finally, we present a minimalistic yet competitive baseline for OCGL, inspired by our benchmarking results, that achieves strong empirical performance with high efficiency.

cs.LG↗
arXiv2025

Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games

Equilibrium learning in adversarial games is an important topic widely examined in the fields of game theory and reinforcement learning (RL). Pursuit-evasion game (PEG), as an important class of real-world games from the fields of robotics and security, requires exponential time to be accurately solved. When the underlying graph structure varies, even the state-of-the-art RL methods require recomputation or at least fine-tuning, which can be time-consuming and impair real-time applicability. This paper proposes an Equilibrium Policy Generalization (EPG) framework to effectively learn a generalized policy with robust cross-graph zero-shot performance. In the context of PEGs, our framework is generally applicable to both pursuer and evader sides in both no-exit and multi-exit scenarios. These two generalizability properties, to our knowledge, are the first to appear in this domain. The core idea of the EPG framework is to train an RL policy across different graph structures against the equilibrium policy for each single graph. To construct an equilibrium oracle for single-graph policies, we present a dynamic programming (DP) algorithm that provably generates pure-strategy Nash equilibrium with near-optimal time complexity. To guarantee scalability with respect to pursuer number, we further extend DP and RL by designing a grouping mechanism and a sequence model for joint policy decomposition, respectively. Experimental results show that, using equilibrium guidance and a distance feature proposed for cross-graph PEG training, the EPG framework guarantees desirable zero-shot performance in various unseen real-world graphs. Besides, when trained under an equilibrium heuristic proposed for the graphs with exits, our generalized pursuer policy can even match the performance of the fine-tuned policies from the state-of-the-art PEG methods.

cs.LG↗
arXiv2025

BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training

Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy consumption. These advantages make them particularly well suited for deployment on resource-constrained devices. However, training BNNs via gradient-based optimization remains challenging due to the discrete nature of their variables. The dominant approach, quantization-aware training, circumvents this issue by employing surrogate gradients. Yet, this method requires maintaining latent full-precision parameters and performing the backward pass with floating-point arithmetic, thereby forfeiting the efficiency of binary operations during training. While alternative approaches based on local learning rules exist, they are unsuitable for global credit assignment and for back-propagating errors in multi-layer architectures. This paper introduces Binary Error Propagation (BEP), the first learning algorithm to establish a principled, discrete analog of the backpropagation chain rule. This mechanism enables error signals, represented as binary vectors, to be propagated backward through multiple layers of a neural network. BEP operates entirely on binary variables, with all forward and backward computations performed using only bitwise operations. Crucially, this makes BEP the first solution to enable end-to-end binary training for recurrent neural network architectures. We validate the effectiveness of BEP on both multi-layer perceptrons and recurrent neural networks, demonstrating gains of up to +6.89% and +10.57% in test accuracy, respectively. The proposed algorithm is released as an open-source repository.

cs.LG↗
arXiv2025

Compensating Distribution Drifts in Class-incremental Learning of Pre-trained Vision Transformers

Recent advances have shown that sequential fine-tuning (SeqFT) of pre-trained vision transformers (ViTs), followed by classifier refinement using approximate distributions of class features, can be an effective strategy for class-incremental learning (CIL). However, this approach is susceptible to distribution drift, caused by the sequential optimization of shared backbone parameters. This results in a mismatch between the distributions of the previously learned classes and that of the updater model, ultimately degrading the effectiveness of classifier performance over time. To address this issue, we introduce a latent space transition operator and propose Sequential Learning with Drift Compensation (SLDC). SLDC aims to align feature distributions across tasks to mitigate the impact of drift. First, we present a linear variant of SLDC, which learns a linear operator by solving a regularized least-squares problem that maps features before and after fine-tuning. Next, we extend this with a weakly nonlinear SLDC variant, which assumes that the ideal transition operator lies between purely linear and fully nonlinear transformations. This is implemented using learnable, weakly nonlinear mappings that balance flexibility and generalization. To further reduce representation drift, we apply knowledge distillation (KD) in both algorithmic variants. Extensive experiments on standard CIL benchmarks demonstrate that SLDC significantly improves the performance of SeqFT. Notably, by combining KD to address representation drift with SLDC to compensate distribution drift, SeqFT achieves performance comparable to joint training across all evaluated datasets. Code: https://github.com/raoxuan98-hash/sldc.git.

cs.CV↗
arXiv2025

Over-squashing in Spatiotemporal Graph Neural Networks

Graph Neural Networks (GNNs) have achieved remarkable success across various domains. However, recent theoretical advances have identified fundamental limitations in their information propagation capabilities, such as over-squashing, where distant nodes fail to effectively exchange information. While extensively studied in static contexts, this issue remains unexplored in Spatiotemporal GNNs (STGNNs), which process sequences associated with graph nodes. Nonetheless, the temporal dimension amplifies this challenge by increasing the information that must be propagated. In this work, we formalize the spatiotemporal over-squashing problem and demonstrate its distinct characteristics compared to the static case. Our analysis reveals that, counterintuitively, convolutional STGNNs favor information propagation from points temporally distant rather than close in time. Moreover, we prove that architectures that follow either time-and-space or time-then-space processing paradigms are equally affected by this phenomenon, providing theoretical justification for computationally efficient implementations. We validate our findings on synthetic and real-world datasets, providing deeper insights into their operational dynamics and principled guidance for more effective designs.

cs.LG↗
arXiv2025

The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning

Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offline training on task-specific subgraphs is not feasible. In this work, we explore a surprisingly simple yet highly effective approach for OCGL: we use a fixed, randomly initialized encoder to generate robust and expressive node embeddings by aggregating neighborhood information, training online only a lightweight classifier. By freezing the encoder, we eliminate drifts of the representation parameters, a key source of forgetting, obtaining embeddings that are both expressive and stable. When evaluated across several OCGL benchmarks, despite its simplicity and lack of memory buffer, this approach yields consistent gains over state-of-the-art methods, with surprising improvements of up to 30% and performance often approaching that of the joint offline-training upper bound. These results suggest that in OCGL, catastrophic forgetting can be minimized without complex replay or regularization by embracing architectural simplicity and stability.

cs.LG↗
arXiv2025

Preference Isolation Forest for Structure-based Anomaly Detection

We address the problem of detecting anomalies as samples that do not conform to structured patterns represented by low-dimensional manifolds. To this end, we conceive a general anomaly detection framework called Preference Isolation Forest (PIF), that combines the benefits of adaptive isolation-based methods with the flexibility of preference embedding. The key intuition is to embed the data into a high-dimensional preference space by fitting low-dimensional manifolds, and to identify anomalies as isolated points. We propose three isolation approaches to identify anomalies: $i$) Voronoi-iForest, the most general solution, $ii$) RuzHash-iForest, that avoids explicit computation of distances via Local Sensitive Hashing, and $iii$) Sliding-PIF, that leverages a locality prior to improve efficiency and effectiveness.

cs.LG↗
arXiv2025

Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning

Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing mechanisms that facilitate coordination and high-level planning. Specifically, coordination and temporal abstraction can be achieved through communication (e.g., message passing) and Hierarchical Reinforcement Learning (HRL) approaches to decision-making. However, optimization issues limit the applicability of hierarchical policies to multi-agent systems. As such, the combination of these approaches has not been fully explored. To fill this void, we propose a novel and effective methodology for learning multi-agent hierarchies of message-passing policies. We adopt the feudal HRL framework and rely on a hierarchical graph structure for planning and coordination among agents. Agents at lower levels in the hierarchy receive goals from the upper levels and exchange messages with neighboring agents at the same level. To learn hierarchical multi-agent policies, we design a novel reward-assignment method based on training the lower-level policies to maximize the advantage function associated with the upper levels. Results on relevant benchmarks show that our method performs favorably compared to the state of the art.

cs.LG↗