Nikolaos Dimitriadis

Nikolaos Dimitriadis, Francois Fleuret, Pascal Frossard

Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge. While existing frameworks are built on PyTorch, the rising popularity of JAX might lead to divergent codebases, ultimately hindering reproducibility and progress. To address this problem, we introduce SequeL, a flexible and extensible library for Continual Learning that supports both PyTorch and JAX frameworks. SequeL provides a unified interface for a wide range of Continual Learning algorithms, including regularization-based approaches, replay-based approaches, and hybrid approaches. The library is designed towards modularity and simplicity, making the API suitable for both researchers and practitioners. We release SequeL\footnote{\url{https://github.com/nik-dim/sequel}} as an open-source library, enabling researchers and developers to easily experiment and extend the library for their own purposes.

Nikolaos Dimitriadis, Pascal Frossard, François Fleuret

In Multi-Task Learning (MTL), tasks may compete and limit the performance achieved on each other, rather than guiding the optimization to a solution, superior to all its single-task trained counterparts. Since there is often not a unique solution optimal for all tasks, practitioners have to balance tradeoffs between tasks' performance, and resort to optimality in the Pareto sense. Most MTL methodologies either completely neglect this aspect, and instead of aiming at learning a Pareto Front, produce one solution predefined by their optimization schemes, or produce diverse but discrete solutions. Recent approaches parameterize the Pareto Front via neural networks, leading to complex mappings from tradeoff to objective space. In this paper, we conjecture that the Pareto Front admits a linear parameterization in parameter space, which leads us to propose \textit{Pareto Manifold Learning}, an ensembling method in weight space. Our approach produces a continuous Pareto Front in a single training run, that allows to modulate the performance on each task during inference. Experiments on multi-task learning benchmarks, ranging from image classification to tabular datasets and scene understanding, show that \textit{Pareto Manifold Learning} outperforms state-of-the-art single-point algorithms, while learning a better Pareto parameterization than multi-point baselines.

Nikolaos Dimitriadis, Pascal Frossard, Francois Fleuret

Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary to traditional Multi-Task Learning (MTL) that optimizes for a single trade-off decided prior to training. However, recent PFL methodologies suffer from limited scalability, slow convergence, and excessive memory requirements, while exhibiting inconsistent mappings from preference to objective space. We introduce PaLoRA, a novel parameter-efficient method that addresses these limitations in two ways. First, we augment any neural network architecture with task-specific low-rank adapters and continuously parameterize the PF in their convex hull. Our approach steers the original model and the adapters towards learning general and task-specific features, respectively. Second, we propose a deterministic sampling schedule of preference vectors that reinforces this division of labor, enabling faster convergence and strengthening the validity of the mapping from preference to objective space throughout training. Our experiments show that PaLoRA outperforms state-of-the-art MTL and PFL baselines across various datasets, scales to large networks, reducing the memory overhead $23.8-31.7$ times compared with competing PFL baselines in scene understanding benchmarks.

Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture search (NAS) methods have omitted resource utilization, preventing DNNs to take full advantage of the target inference platforms. Modeling resource utilization efficiently and accurately is challenging, especially for widely-used array-based inference accelerators such as Google TPU. In this work, we propose a novel hardware-aware NAS framework that does not only optimize for task accuracy and inference latency, but also for resource utilization. We also propose and validate a new computational model for resource utilization in inference accelerators. By using the proposed NAS framework and the proposed resource utilization model, we achieve 2.8 - 4x speedup for DNN inference compared to prior hardware-aware NAS methods while attaining similar or improved accuracy in image classification on CIFAR-10 and Imagenet-100 datasets.

Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard

Finding optimal channel dimensions (i.e., the number of filters in DNN layers) is essential to design DNNs that perform well under computational resource constraints. Recent work in neural architecture search aims at automating the optimization of the DNN model implementation. However, existing neural architecture search methods for channel dimensions rely on fixed search spaces, which prevents achieving an efficient and fully automated solution. In this work, we propose a novel differentiable neural architecture search method with an efficient dynamic channel allocation algorithm to enable a flexible search space for channel dimensions. We show that the proposed framework is able to find DNN architectures that are equivalent to previous methods in task accuracy and inference latency for the CIFAR-10 dataset with an improvement of $1.3-1.7\times$ in GPU-hours and $1.5-1.7\times$ in the memory requirements during the architecture search stage. Moreover, the proposed frameworks do not require a well-engineered search space a priori, which is an important step towards fully automated design of DNN architectures.

Kyle Matoba, Nikolaos Dimitriadis, François Fleuret

Over the decade since deep neural networks became state of the art image classifiers there has been a tendency towards less use of max pooling: the function that takes the largest of nearby pixels in an image. Since max pooling featured prominently in earlier generations of image classifiers, we wish to understand this trend, and whether it is justified. We develop a theoretical framework analyzing ReLU based approximations to max pooling, and prove a sense in which max pooling cannot be efficiently replicated using ReLU activations. We analyze the error of a class of optimal approximations, and find that whilst the error can be made exponentially small in the kernel size, doing so requires an exponentially complex approximation. Our work gives a theoretical basis for understanding the trend away from max pooling in newer architectures. We conclude that the main cause of a difference between max pooling and an optimal approximation, a prevalent large difference between the max and other values within pools, can be overcome with other architectural decisions, or is not prevalent in natural images.

Ke Wang, Nikolaos Dimitriadis, Alessandro Favero et al. · cambridge

Fine-tuning pre-trained models has become the standard approach to endow them with specialized knowledge, but it poses fundamental challenges. In particular, \textit{(i)} fine-tuning often leads to catastrophic forgetting, where improvements on a target domain degrade generalization on other tasks, and \textit{(ii)} merging fine-tuned checkpoints from disparate tasks can lead to significant performance loss. To address these challenges, we introduce LiNeS, Layer-increasing Network Scaling, a post-training editing technique designed to preserve pre-trained generalization while enhancing fine-tuned task performance. LiNeS scales parameter updates linearly based on their layer depth within the network, maintaining shallow layers close to their pre-trained values to preserve general features while allowing deeper layers to retain task-specific representations. In multi-task model merging scenarios, layer-wise scaling of merged parameters reduces negative task interference. LiNeS demonstrates significant improvements in both single-task and multi-task settings across various benchmarks in vision and natural language processing. It mitigates forgetting, enhances out-of-distribution generalization, integrates seamlessly with existing multi-task model merging baselines improving their performance across benchmarks and model sizes, and can boost generalization when merging LLM policies aligned with different rewards via RLHF. Our method is simple to implement, computationally efficient and complementary to many existing techniques. Our source code is available at https://github.com/wang-kee/LiNeS

Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh et al.

Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data. Weight-space ensembling methods, such as Model Soups, mitigate this effect by averaging multiple checkpoints, but they are computationally prohibitive, requiring the training and storage of dozens of fine-tuned models. In this paper, we introduce MonoSoup, a simple, data-free, hyperparameter-free, post-hoc method that achieves a strong ID-OOD balance using only a single checkpoint. Our method applies Singular Value Decomposition (SVD) to each layer's update and decomposes it into high-energy directions that capture task-specific adaptation and low-energy directions that introduce noise but may still encode residual signals useful for robustness. MonoSoup then uses entropy-based effective rank to automatically re-weigh these components with layer-wise coefficients that account for the spectral and geometric structure of the model. Experiments on CLIP models fine-tuned on ImageNet and evaluated under natural distribution shifts, as well as on Qwen language models tested on mathematical reasoning and multiple-choice benchmarks, show that this plug-and-play approach is a practical and effective alternative to multi-checkpoint methods, retaining much of their benefits without their computational overhead.

Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez et al.

Model merging and task arithmetic have emerged as promising scalable approaches to merge multiple single-task checkpoints to one multi-task model, but their applicability is reduced by significant performance loss. Previous works have linked these drops to interference in the weight space and erasure of important task-specific features. Instead, in this work we show that the information required to solve each task is still preserved after merging as different tasks mostly use non-overlapping sets of weights. We propose TALL-masks, a method to identify these task supports given a collection of task vectors and show that one can retrieve >99% of the single task accuracy by applying our masks to the multi-task vector, effectively compressing the individual checkpoints. We study the statistics of intersections among constructed masks and reveal the existence of selfish and catastrophic weights, i.e., parameters that are important exclusively to one task and irrelevant to all tasks but detrimental to multi-task fusion. For this reason, we propose Consensus Merging, an algorithm that eliminates such weights and improves the general performance of existing model merging approaches. Our experiments in vision and NLP benchmarks with up to 20 tasks, show that Consensus Merging consistently improves existing approaches. Furthermore, our proposed compression scheme reduces storage from 57Gb to 8.2Gb while retaining 99.7% of original performance.

Ke Wang, Yiming Qin, Nikolaos Dimitriadis et al. · cambridge

Language models deployed in real-world systems often require post-hoc updates to incorporate new or corrected knowledge. However, editing such models efficiently and reliably-without retraining or forgetting previous information-remains a major challenge. Existing methods for lifelong model editing either compromise generalization, interfere with past edits, or fail to scale to long editing sequences. We propose MEMOIR, a novel scalable framework that injects knowledge through a residual memory, i.e., a dedicated parameter module, while preserving the core capabilities of the pre-trained model. By sparsifying input activations through sample-dependent masks, MEMOIR confines each edit to a distinct subset of the memory parameters, minimizing interference among edits. At inference, it identifies relevant edits by comparing the sparse activation patterns of new queries to those stored during editing. This enables generalization to rephrased queries by activating only the relevant knowledge while suppressing unnecessary memory activation for unrelated prompts. Experiments on question answering, hallucination correction, and out-of-distribution generalization benchmarks for LLaMA-3 and Mistral backbones demonstrate that MEMOIR achieves state-of-the-art performance across reliability, generalization, and locality metrics, scaling to thousands of sequential edits with minimal forgetting.

Juan Garcia Giraldo, Nikolaos Dimitriadis, Ke Wang et al.

Model merging is a flexible and computationally tractable approach to merge single-task checkpoints into a multi-task model. Prior work has solely focused on constrained multi-task settings where there is a one-to-one mapping between a sample and a task, overlooking the paradigm where multiple tasks may operate on the same sample, e.g., scene understanding. In this paper, we focus on the multi-task setting with single-input-multiple-outputs (SIMO) and show that it qualitatively differs from the single-input-single-output model merging settings studied in the literature due to the existence of task-specific decoders and diverse loss objectives. We identify that existing model merging methods lead to significant performance degradation, primarily due to representation misalignment between the merged encoder and task-specific decoders. We propose two simple and efficient fixes for the SIMO setting to re-align the feature representation after merging. Compared to joint fine-tuning, our approach is computationally effective and flexible, and sheds light into identifying task relationships in an offline manner. Experiments on NYUv2, Cityscapes, and a subset of the Taskonomy dataset demonstrate: (1) task arithmetic suffices to enable multi-task capabilities; however, the representations generated by the merged encoder has to be re-aligned with the task-specific heads; (2) the proposed architecture rivals traditional multi-task learning in performance but requires fewer samples and training steps by leveraging the existence of task-specific models.

Nikolaos Dimitriadis, Petros Maragos

In this paper we study an emerging class of neural networks based on the morphological operators of dilation and erosion. We explore these networks mathematically from a tropical geometry perspective as well as mathematical morphology. Our contributions are threefold. First, we examine the training of morphological networks via Difference-of-Convex programming methods and extend a binary morphological classifier to multiclass tasks. Second, we focus on the sparsity of dense morphological networks trained via gradient descent algorithms and compare their performance to their linear counterparts under heavy pruning, showing that the morphological networks cope far better and are characterized with superior compression capabilities. Our approach incorporates the effect of the training optimizer used and offers quantitative and qualitative explanations. Finally, we study how the architectural structure of a morphological network can affect shape constraints, focusing on monotonicity. Via Maslov Dequantization, we obtain a softened version of a known architecture and show how this approach can improve training convergence and performance.