arXiv:2608. 04545v1 Announce Type: new Abstract: We study the problem of learning compact rule-based compressors for structured network traffic.
arXiv:2608.21874v1 Announce Type: cross Abstract: Deep learning has achieved strong performance in encrypted traffic classification (ETC), yet its computational cost limits deployment on resource-con...
arXiv:2603.25507v2 Announce Type: replace-cross Abstract: Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its practical deployment is often constrained by limited...
The paper introduces Layer-wise Budgeted Adaptive Transmission (LBAT), a method that treats federated learning communication as a resource allocation problem under tight uplink budgets. LBAT estimates the transmission value of each layer using local training signals and then applies a byte‑level dynamic programming allocator to choose optimal rank and bit configurations for each layer. Experiments on heterogeneous federated tabular prediction and data generation tasks show that LBAT outperforms uniform compression baselines, achieving better communication‑utility tradeoffs while maintaining distributional fidelity.
arXiv:2506. 01260v2 Announce Type: replace Abstract: Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks.
The paper explores how to combine Federated Learning with TinyML model compression techniques—such as knowledge distillation, structured pruning, and quantization—to create lightweight, privacy‑preserving intrusion detection systems for IoT devices. It evaluates these strategies within a federated training pipeline and finds that training stability is crucial; a server‑coordinated cosine learning‑rate schedule boosts Attack Recall from 46.7% to 93.85% while still allowing significant model compression and efficient edge deployment.
The paper discusses how any lossless compression algorithm can be transformed into a machine learning method using Normalized Compression Distance or the Minimum Description Length principle, and conversely how any auto‑regressive model can become a lossless compressor via entropy coding. It surveys and formalizes these strategies, introduces a design framework for compression‑based ML, and empirically validates that such methods can match conventional baselines and outperform them on malware detection, achieving accuracy gains up to 0.62 by varying design choices.
arXiv:2609.24455v1 Announce Type: cross Abstract: Intelligent transportation systems require Incremental Learning (IL) to continually improve their overall performance in dynamic environments. Howeve...
ModSec-Learn enhances the open-source Web Application Firewall ModSecurity by integrating a machine‑learning model that uses the Core Rule Set (CRS) as input features. The model learns to adjust the weight of each CRS rule, tailoring severity levels to specific web applications and improving the balance between detection and false positives. Additionally, sparse regularization can eliminate over 30% of CRS rules, simplifying inference while maintaining performance.
arXiv:2607. 17913v1 Announce Type: cross Abstract: Distributed Fine-Tuning (DFT) of large-scale Foundation Models (FMs) on resource-constrained edge devices is limited by local compute constraints and communication overhead.
MoRA is a framework for pruning Mixture-of-Experts (MoE) models by learning a router bias for each expert and optimizing it with a language‑modeling loss and a routing‑diversity regularizer. The learned biases sharpen routing distributions to identify critical experts and encourage diverse routing preferences. After pruning, MoRA uses an expert approximation mechanism that approximates the outputs of pruned experts with affine transformations of remaining experts, further improving performance.
arXiv:2608. 16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices.
The paper introduces mixed integer linear programming (MILP) formulations for training sparse disjunctive normal form (DNF) networks, which are small networks with a conjunctive hidden layer and a disjunctive output layer. By fixing the network structure and optimizing weights, the authors achieve globally optimized rule sets that balance misclassification costs against sparsity. Their enhanced formulation reduces integer decision variables and redundant constraints, and a combined initialization and dropout approach breaks weight symmetries to promote diverse, stable rule representations, leading to improved computational efficiency and competitive accuracy on synthetic and UCI datasets.