Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs

2025-05-29

AI Summary

EC-GCD (Event-Centric Generalized Category Discovery) faces two key challenges: (1) inconsistency between clustering and classification groupings due to subjective labeling, and (2) unfair representation of minority classes. To address these, we propose PaMA—a novel framework featuring: (i) an event-pattern extraction-and-refinement mechanism that aligns clustering and classification semantics; and (ii) a rank-filter-mine pipeline with dynamic prototype-balanced sampling to ensure equitable representation of minority classes in long-text, highly imbalanced settings. PaMA integrates large language model–driven event pattern mining, contrastive latent-space alignment, and H-score–based optimization. Evaluated on our newly constructed EC-GCD benchmark (e.g., Scam Report), PaMA achieves a 12.58% absolute improvement in H-score. Moreover, it demonstrates strong generalization on standard GCD benchmarks, confirming its robustness across diverse category-discovery scenarios.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Clustering
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Generalized Category Discovery (GCD) aims to classify both known and novel categories using partially labeled data that contains only known classes. Despite achieving strong performance on existing benchmarks, current textual GCD methods lack sufficient validation in realistic settings. We introduce Event-Centric GCD (EC-GCD), characterized by long, complex narratives and highly imbalanced class distributions, posing two main challenges: (1) divergent clustering versus classification groupings caused by subjective criteria, and (2) Unfair alignment for minority classes. To tackle these, we propose PaMA, a framework leveraging LLMs to extract and refine event patterns for improved cluster-class alignment. Additionally, a ranking-filtering-mining pipeline ensures balanced representation of prototypes across imbalanced categories. Evaluations on two EC-GCD benchmarks, including a newly constructed Scam Report dataset, demonstrate that PaMA outperforms prior methods with up to 12.58% H-score gains, while maintaining strong generalization on base GCD datasets.

Problem

• Classify known and novel categories with partial labels
• Address imbalanced class distributions in event-centric contexts
• Improve cluster-class alignment using LLM-extracted event patterns

Innovation

• Leveraging LLMs for event pattern extraction
• Ranking-filtering-mining for balanced prototypes
• Improved cluster-class alignment via PaMA