- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies semi-supervised tabular anomaly detection with a small number of labeled anomalies and contaminated unlabeled data, and proposes TabPFN-AD. The method constructs graphs using inter-instance attention from a frozen TabPFN model, mines potential anomalies through instance-level and group-level scoring, and iteratively updates pseudo-labels in the context set. The authors compare the method against baselines on 17 datasets and report experiments on contamination robustness, component ablations, and different TabPFN versions.
Critical strengths
The problem is practically relevant. Treating all unlabeled instances as normal introduces incorrect supervision into the context of an in-context learning model. Improving context quality to address this issue is a worthwhile research direction. The paper is well written and generally clear.
Critical weaknesses
1.The paper assumes that normal instances have many similar peers and therefore exhibit more dispersed attention, whereas anomalous instances have fewer similar peers and therefore exhibit more concentrated attention. However, this does not hold across all data distributions. In real-world scenarios, anomalies may also form large, recurring patterns or have no similar peers at all. I noticed that Figure 2 primarily presents observations on NB15, but I do not think this is sufficient to establish whether this structural assumption is reliable across other data distributions. Furthermore, the paper selects attention heads based on associations among labeled anomalies and self-similarity, and then treats these heads as capturing same-class associations. My question is whether attention relationships that are useful for a small number of known anomalies are also applicable to unknown anomaly types. 2.Table 3 shows that adding the group-level component improves the average AUPRC from 0.8311 to 0.8469. This shows that the group-level component helps overall detection, but I cannot yet determine whether the gains primarily come from identifying unknown anomaly types. Figure 3(c) illustrates the mining of known and unknown anomalies on NB15. However, the main text does not clearly explain how known and unknown types are partitioned, nor does it report their test performance separately. I therefore also have questions about the component’s generalization to unknown anomaly types. I would therefore like the authors to clarify: How are known and unknown anomaly types partitioned? How much does the group-level component independently contribute to test performance on unknown anomalies? Could rare normal subgroups also receive high anomaly scores, and how is the corresponding false-positive risk evaluated?
Questions for authors
Please see the specific concerns and questions raised in the Weaknesses section.
2 comments
Thank you for the response.After considering it,I’ll keep my original score.
We thank the reviewer for raising important questions about the attention-structure assumption and the detection of unknown anomalies. We clarify these issues below.
1. Attention-structure assumption and applicability to unknown anomalies.
The observation that normal instances often have more similar peers, whereas anomalies have fewer, serves as an empirical motivation for the instance-level score sI, rather than a necessary assumption for all data distributions. We agree that anomalies may form large recurring patterns or have no similar peers. In the former case, strong connections among anomalies may weaken the degree contrast used by sI. We therefore introduce sG to identify internally compact anomaly subgroups that may be under-ranked by sI.
Attention-head selection is not intended to find heads specific only to the few known anomaly types. Some heads exhibit misleading relationships, such as normal instances assigning higher attention to labeled anomalies than anomalous instances do. C1 removes heads without meaningful anomaly-related associations, while C2 retains heads that preserve local similarity. The selected heads therefore provide a more reliable relational space, without requiring every unknown anomaly to share the same attention pattern as the labeled anomalies.
Within this space, sI mainly exploits associations with labeled anomalies, whereas sG is designed to reduce this dependence. Unknown anomalies need not assign high attention to labeled anomalies; they can be identified by sG when instances of the same unknown type form an internally connected local subgroup. Rare but compact normal subgroups may also receive high sG, but the method does not directly label every compact subgroup as anomalous. Group-level mining is restricted to the low-out-degree candidate set, combines instance- and group-level rankings, and adds only the core instances of the highest-scoring subgroup. Across 17 datasets, the mean anomaly fraction increases from 46.3% among candidate subgroups to 83.4% among selected subgroups, and 89/96 (92.7%) of the core instances added to pseudo-label updates are true anomalies.
2. Known/unknown split and the contribution of sG on NB15.
NB15 provides fine-grained attack-type labels, allowing us to evaluate the contribution of sG to unknown-anomaly detection. We treat DoS, Analysis, Fuzzers, and Reconnaissance as known anomaly types and use them to construct the labeled-anomaly set. Backdoor, Exploits, and Generic receive no labeled examples and are treated as unknown types. These type labels are used only to construct the split and perform post-hoc analysis; they are not used in head selection, subgroup construction, or pseudo-label refinement.
On NB15, adding sG improves AUPRC from 0.7056 to 0.8308, a relative gain of approximately 17.7%. The subgroup-composition analysis further shows that sG discovers local subgroups containing Backdoor, Exploits, and Generic instances, despite receiving labeled examples only from the known types. This result indicates that the selected heads support not only instance-level mining based on known anomalies but also group-level discovery of previously unseen anomaly types through local similarity structure.