{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/supervised-adversarial-contrastive-learning","title":"Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations","arxiv_id":"2306.01505","date":"2023-06-02","proceeding":null,"authors":["Dou Hu","Yinan Bao","Lingwei Wei","Wei Zhou","Songlin Hu"],"abstract":"Extracting generalized and robust representations is a major challenge in emotion recognition in conversations (ERC). To address this, we propose a supervised adversarial contrastive learning (SACL) framework for learning class-spread structured representations in a supervised manner. SACL applies contrast-aware adversarial training to generate worst-case samples and uses joint class-spread contrastive learning to extract structured representations. It can effectively utilize label-level feature consistency and retain fine-grained intra-class features. To avoid the negative impact of adversarial perturbations on context-dependent data, we design a contextual adversarial training (CAT) strategy to learn more diverse features from context and enhance the model's context robustness. Under the framework with CAT, we develop a sequence-based SACL-LSTM to learn label-consistent and context-robust features for ERC. Experiments on three datasets show that SACL-LSTM achieves state-of-the-art performance on ERC. Extended experiments prove the effectiveness of SACL and CAT.","url_abs":"https://arxiv.org/abs/2306.01505v2","url_pdf":"https://arxiv.org/pdf/2306.01505v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"supervised-adversarial-contrastive-learning","repo_url":"https://github.com/zerohd4869/sacl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"emotion-recognition-in-conversation","task_name":"Emotion Recognition in Conversation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/emotion-recognition-in-conversation-on-cmu-2","task":"Emotion Recognition in Conversation","dataset":"CMU-MOSEI-Sentiment","model":"SACL-LSTM","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"38.60","Weighted F1":"25.95"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-4","task":"Emotion Recognition in Conversation","dataset":"EmoryNLP","model":"SACL-LSTM (one seed)","rank_in_archive_order":5,"of":28,"metrics":{"Micro-F1":"43.19","Weighted-F1":"40.47"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-4","task":"Emotion Recognition in Conversation","dataset":"EmoryNLP","model":"SACL-LSTM","rank_in_archive_order":9,"of":28,"metrics":{"Micro-F1":"42.21","Weighted-F1":"39.65"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on","task":"Emotion Recognition in Conversation","dataset":"IEMOCAP","model":"SACL-LSTM (one seed)","rank_in_archive_order":20,"of":59,"metrics":{"Accuracy":"69.62","Weighted-F1":"69.70"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on","task":"Emotion Recognition in Conversation","dataset":"IEMOCAP","model":"SACL-LSTM","rank_in_archive_order":23,"of":59,"metrics":{"Accuracy":"69.08","Weighted-F1":"69.22"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-7","task":"Emotion Recognition in Conversation","dataset":"IEMOCAP-4","model":"SACL-LSTM","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy":"80.70","Weighted F1":"80.74"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-meld","task":"Emotion Recognition in Conversation","dataset":"MELD","model":"SACL-LSTM (one seed)","rank_in_archive_order":13,"of":68,"metrics":{"Accuracy":"67.89","Weighted-F1":"66.86"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-meld","task":"Emotion Recognition in Conversation","dataset":"MELD","model":"SACL-LSTM","rank_in_archive_order":22,"of":68,"metrics":{"Accuracy":"67.51","Weighted-F1":"66.45"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.01505","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}