论文

DiSPaT:用 f-散度自博弈微调 LLM 做表格异常检测

f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models

精选理由

搞表格异常检测的可以看看这篇。它把 f-散度最小化和自博弈训练结合起来,让 LLM 在无标签情况下不断逼近正常数据分布,实验上超过了以往的 LLM 一次性微调方法和经典无监督检测器。做风控、运维监控这类表格异常检测的团队值得试试。

论文提出 DiSPaT,一个面向表格异常检测的自博弈微调框架,核心是把 f-散度最小化的训练目标近似为缩小真实正常数据分布与模型生成样本分布之间的差距。

正文

工作流程采用交替优化:当前策略每轮生成合成样本充当伪异常,判别器学习区分伪异常与真实正常样本,判别信号再反过来驱动策略更新,让模型分布逐步对齐真实正常数据分布。相比以往把表格行序列化成文本后只做一次监督微调的 LLM 方法,DiSPaT 提供了持续收紧正常性描述的训练信号。

作者在多个基准上实验,结果显示 DiSPaT 稳定超过已有 LLM 方法、深度学习方法以及经典无监督检测器。对处理混合数值、类别与文本属性的异构表格数据场景,这提供了一条不依赖异常标签的可行路线。

原文 · arXiv cs.LG

f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models

Anomaly detection in tabular data poses significant challenges due to heterogeneous feature types-mixing numerical, categorical, and textual attributes, which complicate learning meaningful representations of normality. Recent work has applied large language models (LLMs) to this problem by serializing table rows as text sequences, yet these approaches rely on one-shot supervised fine-tuning that offers limited signal to tighten the model's description of normality. We propose DiSPaT, a self-play fine-tuning framework that strengthens the model's understanding of normal data. Building on the theoretical foundation of f-divergence minimization, we derive a tight approximation connecting our training objective to reducing the distributional gap between real normal data and model-generated samples. DiSPaT operates through an alternating optimization: at each iteration, the current policy generates synthetic samples that serve as pseudo-anomalies, while a critic discriminator learns to distinguish these from real normal samples; this signal drives policy updates that progressively align the model distribution with the true normal-data distribution. Extensive experiments on diverse benchmarks demonstrate that DiSPaT consistently outperforms prior LLM-based methods, deep learning approaches, and classical unsupervised detectors for tabular anomaly detection.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括:异常检测、DiSPaT、f-divergence、自博弈微调,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.LG」(@Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash Harandi, Trung Le),经 AITOP 多维评分管线结构化提炼。