Patched-DeltaNet: Token-Level Event-Driven Memory for Linear-Time Anomaly Detection

• URL: http://arxiv.org/abs/2605.27992v1
• Date: Wed, 27 May 2026 05:33:03 GMT
• Title: Patched-DeltaNet: Token-Level Event-Driven Memory for Linear-Time Anomaly Detection
• Abstract summary: Time series anomaly detection is critical for maintaining the reliability of mission-critical systems.<n>We propose Patched-DeltaNet, a novel architecture combining time-series patching with Gated Delta Networks.
• Score: 4.400911960167063
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series anomaly detection is critical for maintaining the reliability of mission-critical systems. While Transformer-based models like PatchTST have shown remarkable performance, their $\mathcal{O}(L^2)$ computational complexity severely limits deployment in resource-constrained environments. In this paper, we propose Patched-DeltaNet, a novel architecture combining time-series patching with Gated Delta Networks. By integrating these paradigms, we hypothesize and demonstrate the emergence of token-level event-driven memory, whereby the patching mechanism extracts local semantic chunks, while the error-driven DeltaNet updates its recurrent state exclusively when significant physical changes, defined as deltas, occur. This synergy effectively filters out background noise and captures sudden anomalous drifts. Our rigorous experiments on the Server Machine Dataset (SMD) benchmark demonstrate the structural superiority and sample efficiency of Patched-DeltaNet. By strictly outperforming recent architectures under unified evaluation constraints and identical compute budgets, our model yields an ROC-AUC of 0.957 and PA-F1 of 0.822, while drastically reducing computational complexity to the theoretical minimum of $\mathcal{O}(L/P)$.

Related papers

• Do Transformers Actually Help Intrusion Detection? A Temporal Sequence Evaluation on CIC-IDS2017 [1.2934180951771597]
  We reformulate CIC-IDS 2017 as a temporal intrusion-detection task by constructing ordered flow sequences from network conversations.<n>The central finding is that padding convention, not architecture, determines the Transformer's performance.<n>We advocate leakage-free splits, explicit padding disclosure, and sequence-aware benchmarking as standard practice in future IDS research.
  arXiv  Detail & Related papers  (2026-06-09T16:57:10Z)
• DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks [54.32016216994156]
  We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise.<n>To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $mathcalO(1)$ footprint for long-horizon tasks.<n>We present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training.
  arXiv  Detail & Related papers  (2026-04-13T03:19:36Z)
• Alternating Gradient Flow Utility: A Unified Metric for Structural Pruning and Dynamic Routing in Deep Networks [52.153950303594684]
  We propose a decoupled kinetic paradigm inspired by Alternating Gradient Flow (AGF)<n>AGF accurately captures the network's structural "kinetic utility"<n>We design a hybrid routing framework that decouples AGF-guided offline structural search from online execution via zero-cost physical priors.
  arXiv  Detail & Related papers  (2026-03-12T18:19:21Z)
• HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference [0.0]
  Hybrid Quantization and Pruning (HQP) framework designed to achieve synergistic model acceleration.<n>HQP framework achieves a peak performance gain of 3.12 times inference speedup and a 55 percent model size reduction.
  arXiv  Detail & Related papers  (2026-02-02T18:17:45Z)
• Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware [0.0]
  Denoising Diffusion Probabilistic Models (DDPMs) have established a new state-of-the-art in generative image synthesis.<n>This study presents a comparative analysis of DDPMs against the emerging Flow Matching paradigm.
  arXiv  Detail & Related papers  (2025-11-24T18:19:42Z)
• PT$^2$-LLM: Post-Training Ternarization for Large Language Models [52.4629647715623]
  Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment.<n>We propose PT$2$-LLM, a post-training ternarization framework tailored for LLMs.<n>At its core is an Asymmetric Ternary Quantizer equipped with a two-stage refinement pipeline.
  arXiv  Detail & Related papers  (2025-09-27T03:01:48Z)
• MesaNet: Sequence Modeling by Locally Optimal Test-Time Training [67.45211108321203]
  We introduce a numerically stable, chunkwise parallelizable version of the recently proposed Mesa layer.<n>We show that optimal test-time training enables reaching lower language modeling perplexity and higher downstream benchmark performance than previous RNNs.
  arXiv  Detail & Related papers  (2025-06-05T16:50:23Z)
• A network-constrain Weibull AFT model for biomarkers discovery [0.0]
  AFTNet is a network-constraint survival analysis method based on the Weibull accelerated failure time (AFT) model. We present an efficient iterative computational algorithm based on the proximal descent gradient method.
  arXiv  Detail & Related papers  (2024-02-28T11:12:53Z)
• Efficient Generative Modeling via Penalized Optimal Transport Network [1.8079016557290342]
  We propose a versatile deep generative model based on the marginally-penalized Wasserstein (MPW) distance.<n>Through the MPW distance, POTNet effectively leverages low-dimensional marginal information to guide the overall alignment of joint distributions.<n>We derive a non-asymptotic bound on the generalization error of the MPW loss and establish convergence rates of the generative distribution learned by POTNet.
  arXiv  Detail & Related papers  (2024-02-16T05:27:05Z)
• SmoothNets: Optimizing CNN architecture design for differentially private deep learning [69.10072367807095]
  DPSGD requires clipping and noising of per-sample gradients. This introduces a reduction in model utility compared to non-private training. We distilled a new model architecture termed SmoothNet, which is characterised by increased robustness to the challenges of DP-SGD training.
  arXiv  Detail & Related papers  (2022-05-09T07:51:54Z)
• CPNet: Cross-Parallel Network for Efficient Anomaly Detection [20.84973451610082]
  Cross-Parallel Network (CPNet) for efficient anomaly detection is proposed here to minimize computations without performance drops. An inter-network shift module is incorporated to capture temporal relationships among sequential frames to enable more accurate future predictions.
  arXiv  Detail & Related papers  (2021-08-10T05:29:37Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)
• Tessellated Wasserstein Auto-Encoders [5.9394103049943485]
  Non-adversarial generative models such as variational auto-encoder (VAE), Wasserstein auto-encoders with maximum mean discrepancy (WAE-MMD), sliced-Wasserstein auto-encoder (SWAE) are relatively easy to train and have less mode collapse compared to Wasserstein auto-encoder with generative adversarial network (WAE-GAN) We develop a novel framework called Tessellated Wasserstein Auto-encoders (TWAE) to tessellate the support of the target distribution into a given number of regions by the centroidal Voronoi t
  arXiv  Detail & Related papers  (2020-05-20T09:21:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.