Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild
This addresses a practical problem for real-world CRE applications by handling noisy data streams, representing an incremental improvement over existing methods that assume clean data.
The paper tackles the problem of continual relation extraction (CRE) in real-world scenarios with noisy labels, formalizing a noisy-CRE setting and developing a noise-resistant contrastive framework called NaCL. The result shows that NaCL achieves consistent performance improvements with increasing noise rates, outperforming state-of-the-art baselines.
The principle of continual relation extraction~(CRE) involves adapting to emerging novel relations while preserving od knowledge. While current endeavors in CRE succeed in preserving old knowledge, they tend to fail when exposed to contaminated data streams. We assume this is attributed to their reliance on an artificial hypothesis that the data stream has no annotation errors, which hinders real-world applications for CRE. Considering the ubiquity of noisy labels in real-world datasets, in this paper, we formalize a more practical learning scenario, termed as \textit{noisy-CRE}. Building upon this challenging setting, we develop a noise-resistant contrastive framework named as \textbf{N}oise-guided \textbf{a}ttack in \textbf{C}ontrative \textbf{L}earning~(NaCL) to learn incremental corrupted relations. Compared to direct noise discarding or inaccessible noise relabeling, we present modifying the feature space to match the given noisy labels via attacking can better enrich contrastive representations. Extensive empirical validations highlight that NaCL can achieve consistent performance improvements with increasing noise rates, outperforming state-of-the-art baselines.