Lune

AAAI2024Top-tier venue

RR-PU: A Synergistic Two-Stage Positive and Unlabeled Learning Framework for Robust Tax Evasion Detection

Shuzhi Cao, Jianfei Ruan, Bo Dong, Bin Shi, Qinghua Zheng

Abstract

Tax evasion, an unlawful practice in which taxpayers deliberately conceal information to avoid paying tax liabilities, poses significant challenges for tax authorities. Effective tax evasion detection is critical for assisting tax authorities in mitigating tax revenue loss. Recently, machine-learning-based methods, particularly those employing positive and unlabeled (PU) learning, have been adopted for tax evasion detection, achieving notable success. However, these methods exhibit two major practical limitations. First, their success heavily relies on the strong assumption that the label frequency (the fraction of identified taxpayers among tax evaders) is known in advance. Second, although some methods attempt to estimate label frequency using approaches like Mixture Proportion Estimation (MPE) without making any assumptions, they subsequently construct a classifier based on the errorprone label frequency obtained from the previous estimation. This two-stage approach may not be optimal, as it neglects error accumulation in classifier training resulting from the estimation bias in the first stage. To address these limitations, we propose a novel PU learning-based tax evasion detection framework called RR-PU, which can revise the bias in a twostage synergistic manner. Specifically, RR-PU refines the label frequency initialization by leveraging a regrouping technique to fortify the MPE perspective. Subsequently, we integrate a trainable slack variable to fine-tune the initial label frequency, concurrently optimizing this variable and the classifier to eliminate latent bias in the initial stage. Experimental results on three real-world tax datasets demonstrate that RR-PU outperforms state-of-the-art methods in tax evasion detection tasks.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective cites A Variational Approach for Learning from Positive and Unlabeled Data
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. Provably End-to-end Label-noise Learning without Anchor PointsXuefeng Li, Tongliang Liu, Bo Han, Gang Niu et al.ICML 2021 · 161 citations
  2. A Variational Approach for Learning from Positive and Unlabeled DataHui Chen, Fangqing Liu, Yin Wang, Liyue Zhao et al.NeurIPS 2020 · 76 citations
  3. Dist-PU: Positive-Unlabeled Learning from a Label Distribution PerspectiveYunrui Zhao, Qianqian Xu, Yangbangyan Jiang, Peisong Wen et al.CVPR 2022 · 47 citations
  4. Rethinking Class-Prior Estimation for Positive-Unlabeled LearningYu Yao, Tongliang Liu, Bo Han, Mingming Gong et al.ICLR 2022 · 24 citations

Related papers

  1. Learning from Positive and Unlabeled Data with Arbitrary Positive ShiftZayd Hammoudeh, Daniel LowdNeurIPS 2020 · 53 citations
  2. Positive Distribution Pollution: Rethinking Positive Unlabeled Learning from a Unified PerspectiveQianqiao Liang, Mengying Zhu, Yan Wang, Xiuyuan Wang et al.AAAI 2023 · 4 citations
  3. Mixture Proportion Estimation and PU Learning: A Modern ApproachSaurabh Garg, Yifan Wu, Alexander J. Smola, Sivaraman Balakrishnan et al.NeurIPS 2021 · 79 citations
  4. Learning from Positive and Unlabeled Multi-Instance Bags in Anomaly DetectionLorenzo Perini, Vincent Vercruyssen, Jesse DavisKDD 2023 · 13 citations
  5. Recovering the Propensity Score from Biased Positive Unlabeled DataWalter Gerych, Thomas Hartvigsen, Luke Buquicchio, Emmanuel Agu et al.AAAI 2022 · 20 citations
Dusk over the sea between two cliffs drawn in fine vertical lines