TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection

Dongchan Cho; Juwon Hwang; Keumyeong Kang; Jiho Han; Namsoon Jung

cs.LGOct 23, 2026

TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection

Authors: Dongchan Cho, Juwon Hwang, Keumyeong Kang, Jiho Han, Namsoon Jung

Organizations: Industrial AI Lab, SimPlatform Co. Ltd. Affiliate Research Institute

Abstract

In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepancy an unreliable indicator of abnormal system behavior. Since latent-space scoring can mitigate this limitation, we reframe one-class MTSAD as current-point system-state compatibility estimation and propose TENET, the Time-point Encoding Network for Multivariate Time Series Anomaly Detection. We define the current-point system state as a latent representation of the target time point, constructed from variable-level temporal context in the input window. TENET constructs this state through a temporal layer that retrieves window context relative to the current point, encodes time with current-point-centered embeddings, and adaptively mixes the retrieved context with the current representation. With this design, TENET treats the input window not as the object to reconstruct, forecast, summarize, or score, but as context for constructing a latent representation evaluated with a fixed standard-normal negative log-likelihood score. Across benchmark datasets, TENET achieves state-of-the-art performance. Additional experiments further show that TENET remains effective under alternative one-class objectives and outperforms substitutions based on generic sequence encoders, suggesting that its advantage comes from decision-aligned representation construction rather than from a specialized scoring rule. These results indicate that one-class MTSAD can be strong when the latent representation is designed around the current time point.

Figures & tables

Figure 1: Architecture of TENET. A temporal layer, an inter-variable layer, and an aggregation layer construct the current-point system state from the input window. The inset shows the Temporal block, which uses anchored cross-attention to retrieve history relative to the current point.

Dataset	PSM (25 vars)				SMD (38 vars)				SWaT (51 vars)				SWAN (38 vars)
Metric	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR
IF	54.23	33.41	56.47	37.78	56.59	15.63	56.21	15.91	36.35	10.27	41.37	10.17	48.96	38.12	52.67	62.27
PCA	65.89	47.32	65.59	47.53	77.11	60.86	76.95	62.14	81.85	72.64	81.77	48.17	72.89	63.16	64.46	72.05
OCSVM	69.29	50.83	69.12	50.97	76.87	61.71	76.52	61.42	81.76	71.80	68.54	42.38	71.36	60.75	63.99	70.90
DAGMM	54.91	32.55	54.80	32.05	78.25	59.90	77.73	19.91	61.96	16.47	36.61	9.67	67.18	55.59	60.08	64.16
THOC	64.17	43.56	64.03	44.19	79.80	62.64	71.41	66.45	55.58	24.19	55.32	27.12	73.11	62.59	58.96	73.52

Table 1: Multivariate time series anomaly detection performance on real-world datasets. All metrics are reported in percent and averaged over five random seeds. Bold indicates the best score.

Objective	NLL				DeepSVDD				THOC				DAGMM
Metric	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR
LSTM	72.08	52.97	71.92	53.09	72.13	53.68	71.96	53.78	66.70	45.62	66.57	45.81	69.96	48.97	67.40	48.64
Dilated RNN	66.02	46.83	65.89	47.02	72.90	53.30	72.70	53.39	60.10	40.33	60.04	40.57	65.83	44.88	65.59	45.06
Mamba	64.98	40.87	64.89	41.10	70.61	46.75	70.47	46.92	66.51	40.53	66.41	40.80	71.15	48.26	70.87	48.36
ModernTCN	74.39	51.69	63.85	49.53	74.23	51.55	63.92	49.45	78.86	54.22	78.80	55.00	73.75	47.78	60.59	44.59
GPT4TS	74.67	45.58	61.04	42.00	66.47	40.99	60.57	41.44	73.27	43.21	60.03	39.69	44.91	31.85	44.94	32.34

Table 2: Encoder and one-class objective comparison on PSM. All metrics are reported in percent and averaged over five random seeds. Bold indicates the best score.

Panel of Figure 2 — Figure 2: Representation diagnostics on PSM across TENET and alternative encoders. (a) Effective rank across epochs, where higher values indicate a more distributed representation. (b) Cumulative explained variance ratio at the final epoch, where a slower rise indicates weaker spectral concentration. (c) V-PR using only the directional component of the state vector, where higher values indicate stronger anomaly-relevant angular structure. (d) V-PR using only the radial component of the state vector, where higher values indicate stronger anomaly-relevant radial structure.

Dataset	PSM (25 vars)				SMD (38 vars)				SWaT (51 vars)				SWAN (38 vars)
Metric	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR
LSTM	66.58	49.38	66.47	49.57	84.70	69.75	84.07	69.84	82.40	72.47	82.31	68.80	63.54	54.41	59.46	67.99
Dilated RNN	66.64	49.36	66.52	49.53	84.91	69.77	84.16	69.77	82.40	72.59	82.30	68.76	64.19	55.41	59.47	68.10
Mamba	76.42	60.64	76.24	60.72	88.97	68.62	88.42	68.35	82.74	62.21	82.66	61.69	80.08	68.76	68.77	74.58
TENET	86.14	74.27	85.82	74.21	90.04	74.78	89.50	74.41	87.78	79.63	87.67	79.45	88.36	84.07	72.98	80.97

Table 3: Architectural variation of the temporal layer within TENET on four benchmark datasets. All metrics are reported in percent and averaged over five random seeds. Bold indicates the best score.

Components				PSM (25 vars)				SMD (38 vars)				SWaT (51 vars)				SWAN (38 vars)
Gating Mech.	Lag Embed.	Per-Var. Encoder	Cross-Var. Attn.	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR
✗	✓	✓	✓	82.07	66.90	81.81	66.91	90.27	73.66	89.71	73.29	86.51	77.07	86.42	76.60	78.72	77.44	64.44	76.06
✓	✗	✓	✓	82.30	67.55	82.01	67.56	88.83	72.90	88.31	72.60	86.08	74.71	85.98	74.39	87.22	81.97	72.10	79.97
✓	✓	✗	✓	54.29	32.18	54.05	32.51	70.49	30.22	70.29	30.49	81.88	72.34	81.84	70.17	83.33	77.01	68.97	76.91
✓	✓	✓	✗	84.70	72.47	84.36	72.41	89.76	74.49	89.22	74.03	87.60	79.09	87.49	78.75	88.18	83.93	72.91	80.96
✓	✓	✓	✓	86.14	74.27	85.82	74.21	90.04	74.78	89.50	74.41	87.78	79.63	87.67	79.45	88.36	84.07	72.98	80.97

Table 4: Component ablation study of TENET on four benchmark datasets. All metrics are reported in percent and averaged over five random seeds. Bold indicates the best score.

Window	L=20				L=50				L=100				L=150
Phase	Inference		Training		Inference		Training		Inference		Training		Inference		Training
Metric	Lat.	Mem.	Lat.	Mem.	Lat.	Mem.	Lat.	Mem.	Lat.	Mem.	Lat.	Mem.	Lat.	Mem.	Lat.	Mem.
N=25	8.30	0.20	39.30	1.01	8.30	0.57	39.90	1.48	8.40	0.58	40.10	2.25	8.40	0.58	50.00	3.02
N=100	32.70	1.48	186.70	3.97	32.80	2.18	189.70	5.82	32.90	2.18	188.70	8.93	32.80	2.19	216.40	11.97
N=400	143.20	5.82	883.90	16.73	144.40	8.60	906.30	24.14	146.70	8.62	910.10	36.55	148.40	8.64	1020.20	48.75

Table 5: Computational scalability of TENET on synthetic data with

d=256

. Latency is reported in milliseconds(ms) and memory in gigabytes(GB).

Panel of Figure 3 — Figure 3: Hyperparameter sensitivity on SWAN. Lines show V-PR (%) averaged over five seeds and shaded regions indicate ${\pm}1$ standard deviation. X-axis settings are equally spaced.

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 9 — Figure S1 : Extended-training stability analysis for TENET on PSM. Panels (a)–(d) show test mean state norm, RMS pairwise distance, effective rank, and cumulative EVR. Panels (e)–(h) report A-ROC, A-PR, V-ROC, and V-PR over training.

Dataset	PSM	SMD	SWaT	SWAN
Features	25	38	51	38
Set size	Train: 132,481	Train: 23,697	Train: 496,800	Train: 60,000
Set size	Test: 87,841	Test: 23,697	Test: 449,919	Test: 60,000
Anomalies	Count: 71	Count: 13	Count: 34	Count: 6,148
Anomalies	Ratio: 27.73%	Ratio: 10.12%	Ratio: 12.02%	Ratio: 32.60%
Segment Lengths	Min: 1	Min: 3	Min: 101	Min: 1

Appendix

Table S1 : Statistics of the benchmark datasets used in the experiments. Anomaly count, anomaly ratio, and segment lengths are computed from the test labels, where count denotes the number of contiguous anomalous segments.

Metric	AUC-ROC	AUC-PR	VUS-ROC	VUS-PR
Granularity	Point-wise	Point-wise	Point+Time	Point+Time
Threshold-Free	Yes	Yes	Yes	Yes
Temporal-Aware	No	No	Yes	Yes
Delay-Tolerant	No	No	Yes	Yes
Imbalance-Robust	No	Yes	Yes	Yes

Appendix

Table S2 : Summary of the evaluation metrics used in the experiments.

Dataset

PSM (25 vars)

SMD (38 vars)

SWaT (51 vars)

SWAN (38 vars)

Method

A-ROC

A-PR

V-ROC

V-PR

A-ROC

A-PR

V-ROC

V-PR

A-ROC

A-PR

V-ROC

V-PR

A-ROC

A-PR

V-ROC

V-PR

–

PCA

–

OCSVM

–

DAGMM

2.86

2.05

2.89

2.77

1.96

3.07

2.02

4.83

6.29

2.35

19.03

15.14

4.66

7.57

2.91

5.00

THOC

3.77

5.00

3.73

4.97

3.77

4.58

10.56

9.99

0.95

1.66

15.79

13.57

3.50

5.78

3.39

3.56

Appendix

Table S3 : Standard deviation of anomaly detection performance on four multivariate time series anomaly detection datasets. All metrics are reported in percent and computed over five random seeds. Lower values indicate higher stability across runs.

Objective	NLL				DeepSVDD				THOC				DAGMM
Metric	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR
LSTM	73.71	64.50	64.30	72.30	78.99	70.41	68.64	76.06	58.26	47.26	55.39	63.39	75.11	68.32	59.33	79.04
Dilated RNN	68.00	57.53	62.11	69.24	79.59	72.75	67.87	76.25	64.48	55.54	60.81	67.86	78.21	71.73	61.55	78.05
Mamba	52.75	36.66	51.85	57.72	82.70	66.93	70.17	73.81	75.18	57.75	64.85	68.22	68.81	51.94	62.21	66.58
ModernTCN	63.38	54.01	58.21	73.65	63.37	53.97	58.14	73.71	63.40	47.90	61.43	66.45	62.01	52.19	57.56	72.38
GPT4TS	80.46	71.79	66.61	77.42	75.89	65.20	61.87	73.64	78.68	69.41	57.97	78.78	47.93	39.02	48.36	58.76

Appendix

Table S4 : Encoder and one-class objective comparison on SWAN. All metrics are reported in percent and averaged over five random seeds. Bold indicates the best score.

Reference	PSM				SMD
Reference	A-ROC	A-PR	V-ROC	V-PR	A-ROC	A-PR	V-ROC	V-PR
Fixed standard normal	$86.14\pm 0.69$	$74.27\pm 1.73$	$85.82\pm 0.68$	$74.21\pm 1.70$	$90.04\pm 1.19$	$74.78\pm 1.63$	$89.50\pm 1.19$	$74.41\pm 1.63$
Learnable Gaussian	$86.20\pm 0.74$	$74.44\pm 1.68$	$85.88\pm 0.73$	$74.38\pm 1.65$	$90.03\pm 0.97$	$74.77\pm 1.27$	$89.50\pm 0.94$	$74.42\pm 1.20$

Appendix

Table S5 : Gaussian reference comparison for TENET on PSM and SMD. Metrics are reported in percent as mean

\pm

standard deviation over five seeds.

Method	Parameters (MB)	Operations (G)	Inference $B=1$ (ms)	Inference $B=64$ (ms)	Training $B=64$ (ms)	Training Peak $B=64$ (MB)
THOC	0.53	0.033	1.67	0.0267	3.63	439.07
OmniAnomaly	1.42	0.035	0.31	0.0059	2.05	224.62
Anomaly Transformer	19.82	0.526	0.85	0.0420	16.51	3,092.85
CATCH	4.39	0.665	1.69	0.4029	85.31	9,441.99
SARAD	38.45	0.986	0.44	0.0581	12.56	1,134.95
DCdetector	3.71	1.848	1.35	0.2530	53.93	8,183.42

Appendix

Table S6 : Cross-model computational cost at

N=L=100

. Inference latency is per window, and training latency is per step.

B

denotes batch size.

Panel of Figure 16 — Figure S2 : Gaussian training perturbation robustness. Panels report V-PR (%) versus perturbation rate (%) across datasets, with mean and $\pm 1$ standard deviation over five seeds.

Panel of Figure 17 — Figure S3 : Uniform training perturbation robustness. Panels report V-PR (%) versus perturbation rate (%) across datasets, with mean and $\pm 1$ standard deviation over five seeds.

Panel of Figure 18 — Figure S4 : Constant-offset training perturbation robustness. Panels report V-PR (%) versus perturbation rate (%) across datasets, with mean and $\pm 1$ standard deviation over five seeds.

Panel of Figure 19 — Figure S5 : Sensitivity of TENET to test-time current-point noise on PSM. Panels report each metric (%) versus noise standard deviation $\sigma$ . Lines and markers show the mean over five seeds, and shaded bands indicate $\pm 1$ standard deviation.

Unsupervised Anomaly Detection

Unsupervised anomaly detection finds unusual patterns without labeled examples of faults, attacks, defects, or other rare events.

See all 222 papers

LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection
Oct 26, 2026Cristhian Moya-Mota, Ignacio Aguilera-Martos, Diego García-Gil +1Time-Series Anomaly Detection Unsupervised Anomaly Detection
Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain. · Andalusian Institute of Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain. · Department of Software Engineering, University of Granada, Granada, Spain
Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector
May 27, 2026Junhao Wei, Yanxiao Li, Bidong Chen +9Graph-Based Anomaly Detection Multi-View Learning
Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, China · 2Macao Polytechnic University, Macao SAR, China
Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series
May 22, 2026Yunhua Pei, Zixing Song, Jin Zheng +1Dynamic Graph Learning Unsupervised Anomaly Detection
School of Computer Science, University of Bristol, Bristol, UK · School of Engineering Mathematics, University of Bristol, Bristol, UK

Oct 26, 2026J/K move · Enter open · S save

LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection

Cristhian Moya-Mota, Ignacio Aguilera-Martos, Diego García-Gil, Julián Luengo

Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain. · Andalusian Institute of Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain. · Department of Software Engineering, University of Granada, Granada, Spain

Time-Series Anomaly Detection Unsupervised Anomaly Detection Time Series Transformers Sequence Modeling

Open paper AskPDF arXiv

Time-series anomaly detection is dominated by reconstruction-based neural detectors, whose objective is structurally flawed. Since the target is also the input, an expressive model can learn to reconstruct anomalies too, leaving uninformative residuals. Recent large-scale benchmarks show that, on curated data, elaborate deep detectors rarely beat simple statistical baselines, while current leaders rely on representation learning. We propose LEAP (Latent Embedding Anomaly Patch-Transformer), which combines masked prediction with latent representation-based anomaly evidence, without relying on reconstruction or attention-based scoring. The model removes patches from a window and predicts them from the remaining temporal and cross-channel context, so prediction errors measure how well learned dynamics explain hidden segments. Deterministic complementary group masking ensures every time step is scored while hidden, with identical visible fractions during training and inference. LEAP adds three label-free evidence sources: latent-embedding novelty calibrated by local density, local temporal contrast, and per-channel novelty pooled over channels selected by six label-free criteria. Under the TSB-AD protocol, the full model achieves a VUS-PR of

0.5179 \pm 0.0022

180

held-out multivariate series. On TSB-AD-U, a univariate variant combining multi-scale masked-prediction scoring with latent novelty, without contrast or channel-pool novelty, achieves

0.6194 \pm 0.0016

350

held-out series. Both results average three random seeds. A five-stage ablation on TSB-AD-M, supported by paired Wilcoxon signed-rank tests, shows statistically significant gains from each successive component.

Abstract

Unsupervised Anomaly Detection

Explore similar work

LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection

Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector

Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series