- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper explores the challenges in graph-based federated fraud detection, including spectral heterogeneity on the client side and the identification of isolated fraudulent nodes. The authors propose a framework called FedSACA, which achieves local adaptation by learning spectral gates and uses the resulting gate values to weight the aggregated client filtering coefficients. Building on this, the authors also introduce FedSACA+; this version constructs neighborhood relationships based on node features and suppresses potential noise introduced by new connections. Experiments conducted on four datasets demonstrate that FedSACA outperforms baseline methods in fraud detection benchmarks.
Critical strengths
- This paper explores the heterogeneity of fraud spectra both within and across clients. By visualizing the spectral energy distribution, the authors highlight the disparities among different clients, providing a clear motivation for employing adaptive spectral learning within a federated learning environment.
- FedSACA features a streamlined and intuitive design that combines local spectral gating with weighted aggregation at the server side. Building upon this, FedSACA+ introduces a feature-based nearest-neighbor graph as a distinct relational structure; it employs a conservative initial gating mechanism to regulate the influence of these added connections, thereby achieving structural enhancement within a unified framework.
- The experimental evaluation encompasses four datasets and a variety of baseline methods. This framework performs better than other baselines.
Critical weaknesses
- The motivation for this study stems primarily from the heterogeneity in the spectral patterns of fraudulent behavior within real-world institutions. However, the graph datasets used in the experiments are partitioned among clients artificially based on a Dirichlet distribution. It remains unclear to what extent this partitioning accurately represents clients in real-world institutional settings, nor is it clear whether the observed differences in spectral patterns arise from distinct fraudulent mechanisms or from topological changes induced by the graph partitioning process itself. Please provide the full details of the data partitioning scheme and evaluate the proposed method under varying degrees of heterogeneity.
- In Section 4.1, the authors state that fraudsters manipulate local connectivity to blend in with legitimate nodes. Please clarify which relationship types or operations in the dataset correspond to this behavior, and provide relevant examples, statistical data, or references.
- In Equation (7), is a gating weight learned jointly with the filter coefficients; in Equation (14), this weight is used to determine the contribution of each client during the aggregation process. Could the authors explain why a larger gating weight implies that the knowledge provided by a client is more reliable? To isolate the contribution of confidence-aware weighting, could the authors conduct an experiment where only Equation (14) is modified? For instance, replace it with uniform weighting.
Questions for authors
Please refer to my weaknesses.
4 comments
Thank you for your clear explanation. I have decided to maintain my score.
Response to Reviewer jmy6 (2/3)
W3: Justification of
We thank the reviewer for raising this important question. We clarify that is a task-driven spectral confidence score, rather than a manually assigned weight. Its learning mechanism and its role in aggregation can be understood from two complementary perspectives.
1. Gradient-based learning of task-dependent spectral confidence.
Recall that the filtered representation is
$ H_i=\sum_{k=0}^{K-1}s_{i,k}\theta_{i,k}V_{i,k}, \quad V_{i,k}=T_k(\hat A_i)X_i. $
Let
$ G_{i,k}= \left\langle \nabla_{H_i}\mathcal L_{\mathrm{CE}}^{(i)}, V_{i,k} \right\rangle_F. $
By the chain rule, the gradient of the local objective with respect to the confidence mask is
Ignoring the proximal term momentarily, gradient descent increases when
$ -\theta_{i,k}G_{i,k}>\lambda. $
This condition indicates that the corresponding spectral component provides sufficient reduction in the local fraud detection loss to overcome the sparsity penalty. Conversely, components that provide insufficient predictive utility are progressively suppressed.
Therefore, is learned according to the task-dependent contribution of each spectral basis, rather than being assigned independently of the downstream objective. Importantly, this mechanism also accounts for the sign of , since the gradient depends on the actual contribution of the basis to the prediction loss.
2. Theoretical motivation for confidence-aware aggregation.
The use of confidence scores in aggregation is also motivated by inverse-variance weighting.
Consider a fixed spectral coefficient , and suppose each client provides an unbiased estimate
$ \theta_{i,k}=\theta_k^*+\epsilon_{i,k}, $
where the estimation errors are independent, zero-mean, and have variances .
For a linear unbiased estimator
$ \hat\theta_k=\sum_i\alpha_{i,k}\theta_{i,k}, \qquad \sum_i\alpha_{i,k}=1, $
its variance is
$ \operatorname{Var}(\hat\theta_k) =\sum_i\alpha_{i,k}^2\sigma_{i,k}^2. $
Minimizing this variance under the unbiasedness constraint yields
Thus, clients with more reliable coefficient estimates (lower estimation variance) should receive larger aggregation weights.
FedSACA adopts the corresponding confidence-weighted form:
Under the condition that the learned confidence scores are positively associated with coefficient estimation precision, i.e., , Eq. (14) recovers the minimum-variance aggregation weights.
We emphasize that this result provides a theoretical justification for precision-aware weighting, while the correspondence between the learned gates and actual client reliability is an empirical property that we further investigate below.
Response to Reviewer jmy6 (3/3)
3. Empirical validation of learned confidence.
We conduct two complementary experiments.
First, we measure the independent predictive utility of each spectral basis through leave-one-basis-out retraining. Specifically, we define
where is retrained with the -th basis disabled. A positive value indicates that the basis contributes to better validation performance. We then examine the rank correlation between the learned confidence and its independently measured utility, controlling for the magnitude of and the basis representation norm.
| Dataset | Spearman ρ(s,U) ↑ | Partial ρ ↑ | Top-2 Utility-positive Rate ↑ |
|---|---|---|---|
| YelpChi | 0.74 | 0.61 | 86.7% |
| Amazon | 0.69 | 0.55 | 83.3% |
| FDCompCN | 0.78 | 0.65 | 90.0% |
| Elliptic | 0.72 | 0.58 | 86.7% |
| Average | 0.73 | 0.60 | 86.7% |
Table 1: Faithfulness of Learned Confidence to Spectral Basis Utility
As shown in Table 1, the learned confidence scores exhibit consistently strong positive correlations with independently measured basis utility across all four datasets (Spearman , averaging ). Importantly, these correlations remain positive after controlling for the filter coefficient magnitude and basis representation norm (partial , averaging . Moreover, an average of % of the top-2 highest-confidence bases exhibit positive predictive utility. These findings support that the learned confidence scores reflect task-relevant spectral basis importance, rather than merely their multiplicative contribution to the filtering operation.
Second, to verify whether the learned confidence scores provide useful information for cross-client aggregation, we compare the original Eq. (14) against uniform aggregation and randomly permuted confidence weights. The permutation preserves the distribution of confidence scores while breaking their correspondence with the respective client coefficients. We keep the remaining aggregation procedure, including Eq. (13), unchanged.
| Dataset | Learned s (AUC/F1) ↑ | Uniform (AUC/F1) ↑ | Permuted s (AUC/F1) ↑ | ΔAUC vs. Permuted ↑ |
|---|---|---|---|---|
| YelpChi | 89.8 / 74.4 | 84.1 / 70.3 | 80.9 / 66.0 | +8.9 |
| Amazon | 99.3 / 92.2 | 95.4 / 89.8 | 91.2 / 85.4 | +8.1 |
| FDCompCN | 76.2 / 68.0 | 70.0 / 62.0 | 61.2 / 57.6 | +15.0 |
| Elliptic | 99.2 / 93.6 | 93.5 / 88.1 | 88.4 / 82.9 | +10.8 |
Table 2: Effectiveness of Learned Confidence in Federated Aggregation
As shown in the above Table 2, confidence-aware aggregation consistently outperforms uniform averaging by – AUC points (averaging ) across all four datasets. More importantly, randomly permuting the learned confidence scores leads to substantially larger performance degradation, with AUC dropping by – points (averaging ). Since permutation preserves the confidence distribution but disrupts its correspondence with client coefficients, these results suggest that the learned scores encode useful client-specific information for knowledge aggregation. Together with Table 1, these findings support interpreting as a task-conditioned confidence proxy that reflects spectral basis relevance and provides informative weights for federated aggregation.
As shown in our newly added ablation study in the revised appendix (Variant B in Table 4), this uniform aggregation yields an AUC of %, which is significantly lower than the % achieved by our full confidence-aware aggregation (Variant C/FedSACA). This large performance gap (drop of %) strongly validates that weighting by confidence effectively prevents the global filter from being polluted by clients' conflicting and unreliable spectral preferences, proving the necessity of our design.
Thank you again. Please let us know if our answers address your concerns, or whether we can provide further clarifications. We hope the new results and clarifications support a stronger acceptance rating.
Response to Reviewer jmy6 (1/3)
We thank the reviewer for their careful reading and constructive suggestions, which helped us strengthen the paper.
W1: Spectral heterogeneity and Dirichlet distribution.
We thank the reviewer for this insightful comment. The Dirichlet-based partitioning is a standard protocol for simulating non-IID data in real-world federated learning (Hsu et al., 2019 [1]; He et al., 2021 [2]). To address whether the observed heterogeneity originates from partitioning, we have added an analysis of the original centralized graph to section E.1 of the revised appendix. As shown in the new Figure 6, the fraud signal energy on the whole graph of YelpChi already exhibits a diverse, non-contiguous spectral profile (i.e., heterogeneity) without any partitioning. The Dirichlet partitioning merely simulates how fraud patterns are distributed naturally within and across clients, thereby exposing inter and intra spectral heterogeneity as exhibited in Figure 1. Furthermore, we have conducted additional experiments with varying degrees of heterogeneity (different Dirichlet α values) in C.3 of the revised appendix, demonstrating that FedSACA+ maintains robust performance.
W2: Fraudster manipulation.
We appreciate the reviewer’s constructive feedback. Our statement in Section 4.1 regarding fraudulent camouflaging is grounded in well-documented empirical findings in real-world fraud detection literature. Taking the YelpChi dataset as an example (e.g., Dou et al., 2020 [3]; Peng et al., 2021 [4]), fraudsters frequently manipulate local connectivity (such as densely reviewing each other via the R-S-R relation) to artificially blend in with benign nodes, forming tight local clusters with elevated connectivity and deceptive homophily at the spatial level. Consequently, relying solely on local spatial aggregations causes GNNs to aggregate massive noise from these camouflaged connections. This renders even camouflage-aware spatial methods (e.g., CARE-GNN) inadequate, as also evidenced by the degraded performance of in Table 1. This critical limitation directly motivates our core argument: to bypass spatial camouflage, we need to capture the distinct fraud patterns from a spectral perspective.
[1] Tzu-Ming Harry Hsu, Hang Qi, and Matthew Brown. Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335, 2019.
[2] Chaoyang He, Keshav Balasubramanian, Emir Ceyani, Carl Yang, Han Xie, Lichao Sun, Lifang He, Liangwei Yang, Philip S Yu, Yu Rong, et al. Fedgraphnn: A federated learning system and benchmark for graph neural networks. In ICLR, 2021a.
[3] Yingtong Dou, Zhiwei Liu, Li Sun, Yutong Deng, Hao Peng, and Philip S Yu. Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In Proceedings of the 29th ACM international conference on information & knowledge management, pp. 315–324, 2020.
[4] Hao Peng, Ruitong Zhang, Yingtong Dou, Renyu Yang, Jingyi Zhang, and Philip S Yu. Reinforced neighborhood selection guided multi-relational graph neural networks. ACM Transactions on Information Systems (TOIS), 40(4):1–46, 2021.