Universal Semantic Enhancement for Weakly Supervised Anomaly Detection

Siyu Zhou; Yuqin Xie; Hao Yuan; Yingjie Zhou

cs.LGOct 16, 2026

Universal Semantic Enhancement for Weakly Supervised Anomaly Detection

Authors: Siyu Zhou, Yuqin Xie, Hao Yuan, Yingjie Zhou

Organizations: Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong · College of Computer Science, Sichuan University, China

Abstract

Weakly supervised anomaly detection on tabular data is an essential task in many label-scarce applications, since tabular data is widely encountered and it is commonly observed in practice that only a limited number of labeled anomalies are available alongside abundant unlabeled samples. Most existing methods try to learn features that capture the inherent distribution patterns in the target domain. However, such features often struggle to provide a complete description of possible abnormal characteristics and are highly susceptible to overfitting the extremely scarce labels. To address this challenge, we propose a weakly supervised anomaly detection method based on universal semantic enhancement for tabular data, which fuses the universal knowledge from a pre-trained tabular foundation model with the domain-specific knowledge learned on the target dataset. The two types of knowledge are naturally complementary: universal semantics describe the common patterns of tabular data across domains, while the domain-specific features capture the inherent distributions of normal and anomalous behaviors in the target dataset. A prototype-conditioned modulation mechanism is then designed to effectively integrate the two types of features, allowing them to reinforce each other for improved anomaly detection. Extensive experiments on public datasets show that the proposed method outperforms competitive methods when only eight labeled anomalies are available in the training procedure.

Figures & tables

Figure 1: Overview of the proposed framework. Universal semantic features $\mathbf{t}_{i}$ are extracted by the frozen pre-trained model, and domain-specific features $(\mathbf{h}_{i},\mathbf{r}_{i},e_{i})$ by the AutoEncoder. Our ProtoFiLM-Dynamic fuses $\mathbf{h}_{i}$ and $\mathbf{t}_{i}$ via per-sample prototype attention to produce the fused representation $\mathbf{f}_{i}$ . The scoring network takes $(\mathbf{r}_{i},\mathbf{f}_{i},e_{i})$ as input and outputs the anomaly score $s_{i}$ . During training, label interpolation between a labeled anomaly and an unlabeled sample with coefficient $\alpha$ generates a pseudo-sample $\mathbf{x}_{\text{mix}}$ whose score is supervised toward the interpolated soft target $\alpha a$ ( $a$ is the score margin); at inference, a zero-parameter score ensemble combines the anomaly score with the pre-trained model’s class probability $p_{t}$ into the final score $s_{\text{final}}$ .

Dataset	RF	CatBoost	DevNet	FEAWAD	PReNet	DeepSAD	TabPFN	Ours
ALOI	0.5130	0.5270	0.5106	0.5187	0.4953	0.5388	0.6098	0.6466
Campaign	0.5323	0.8741	0.5868	0.5893	0.6809	0.6329	0.8570	0.8668
Cardio	0.9256	0.9722	0.8578	0.9469	0.9333	0.9545	0.9870	0.9964
Cardiotocography	0.8212	0.9239	0.8060	0.8171	0.8659	0.8709	0.9340	0.9424
Fault	0.6519	0.7366	0.5863	0.6286	0.6086	0.7574	0.7624	0.7826
Hepatitis	0.8385	0.8154	0.7718	0.7000	0.7846	0.6820	0.8564	0.8827

Table 1: Per-dataset AUROC on 20 representative ADBench datasets (

|\mathcal{M}|=8

, 10 runs). Bold = best, underline = second best. OOM = GPU out of memory. Avg. Rank (20) is computed over the 20 datasets shown, and Avg. Rank (42) over all 42 evaluated datasets.

Figure 2: AUROC (top) and AUPRC (bottom) vs. number of labeled anomalies

|\mathcal{M}|

on five representative datasets. Ours and TabPFN are shown with solid thick lines; all other baselines are shown with semi-transparent dashed lines.

Configuration	AUROC	AUPRC	$\Delta$
Baseline (concat + dev loss)	0.9174	0.7750	—
+ FiLM (static prototype)	0.9178	0.7703	+0.0004
+ ProtoFiLM-Dynamic	0.9238	0.7775	+0.0064
+ RoSAS (loss only)	0.9183	0.7745	+0.0009
+ PDF (score fusion only)	0.9242	0.7782	+0.0068
+ ProtoFiLM-Dynamic + PDF	0.9247	0.7776	+0.0073

Table 3: Component ablation. Each row adds one design choice to the previous configuration.

\Delta

is relative to the ablation baseline AUROC (0.9174).

Figure 3: t-SNE [ 23 ] of the 32-dim penultimate scoring layer on the Waveform dataset (

|\mathcal{M}|=8

, one run). Blue: normal samples (

n=669

); orange: anomalies (

n=20

). Anomaly points in the raw feature space (left) are indistinguishable from normals. The Concat baseline (center) produces partial clustering but with significant normal–anomaly mixing. ProtoFiLM-Dynamic (right) yields a tight, spatially isolated anomaly cluster with a clean decision boundary.

Figure 4: Sensitivity of AUROC (left axis, blue) and AUPR (right axis, orange) to the RoSAS loss weight

\lambda

on 42 datasets (

|\mathcal{M}|=8

, 10 runs). Dashed lines mark the ablation baseline (concat + dev loss) without RoSAS.

Tabular Anomaly Detection

Tabular anomaly detection identifies records whose values or feature relationships depart from expected patterns in structured data.

See all 29 papers

ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes
Mar 19, 2026Jack Yi Wei, Narges ArmanfardTabular Anomaly Detection Tabular Foundation Models
Department of Electrical and Computer Engineering, McGill University, Canada · Mila - Quebec Artificial Intelligence Institute, Montreal, Canada
Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation
Apr 20, 2026Wei Huang, Yuxuan Xiong, Hezhe Qiao +3Tabular Anomaly Detection Pseudo-Labeling
Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark
May 25, 2026Xu Yao, Siyuan Zhou, Zhenbo Wu +6Learning with Noisy Labels Anomaly Detection
Shanghai University of Finance and Economics · Ant Group · Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics

Mar 19, 2026J/K move · Enter open · S save

ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes

Jack Yi Wei, Narges Armanfard

Department of Electrical and Computer Engineering, McGill University, Canada · Mila - Quebec Artificial Intelligence Institute, Montreal, Canada

Tabular Anomaly Detection Tabular Foundation Models Unsupervised Anomaly Detection Tabular ICL

Open paper AskPDF arXiv

Anomaly detection on tabular data is commonly studied under three supervision regimes, including one-class settings that assume access to anomaly-free training samples, fully unsupervised settings with unlabeled and potentially contaminated training data, and semi-supervised settings with limited anomaly labels. Existing deep learning approaches typically train dataset-specific models under the assumption of a single supervision regime, which limits their ability to leverage shared structures across anomaly detection tasks and to adapt to different supervision levels. We propose ICLAD, an in-context learning foundation model for tabular anomaly detection that generalizes across both datasets and supervision regimes. ICLAD is trained via meta-learning on synthetic tabular anomaly detection tasks, and at inference time, the model assigns anomaly scores by conditioning on the training set without updating model weights. Comprehensive experiments on 57 tabular datasets from ADBench show that our method achieves state-of-the-art performance across three supervision regimes, establishing a unified framework for tabular anomaly detection.

Abstract

Tabular Anomaly Detection

Explore similar work

ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes

Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation

Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark