Papers › Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations

Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations

2 Jun 2023arXiv:2306.01505archive 2025-07-28

Dou Hu, Yinan Bao, Lingwei Wei, Wei Zhou, Songlin Hu

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zerohd4869/sacl officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningEmotion RecognitionEmotion Recognition in Conversation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Emotion Recognition in Conversation CMU-MOSEI-Sentiment SACL-LSTM Accuracy 38.60 #7 of 7 Archive leaderboard report
Emotion Recognition in Conversation CMU-MOSEI-Sentiment SACL-LSTM Weighted F1 25.95 #7 of 7 Archive leaderboard report
Emotion Recognition in Conversation EmoryNLP SACL-LSTM (one seed) Micro-F1 43.19 #5 of 28 Archive leaderboard report
Emotion Recognition in Conversation EmoryNLP SACL-LSTM (one seed) Weighted-F1 40.47 #5 of 28 Archive leaderboard report
Emotion Recognition in Conversation EmoryNLP SACL-LSTM Micro-F1 42.21 #9 of 28 Archive leaderboard report
Emotion Recognition in Conversation EmoryNLP SACL-LSTM Weighted-F1 39.65 #9 of 28 Archive leaderboard report
Emotion Recognition in Conversation IEMOCAP SACL-LSTM (one seed) Accuracy 69.62 #20 of 59 Archive leaderboard report
Emotion Recognition in Conversation IEMOCAP SACL-LSTM (one seed) Weighted-F1 69.70 #20 of 59 Archive leaderboard report
Emotion Recognition in Conversation IEMOCAP SACL-LSTM Accuracy 69.08 #23 of 59 Archive leaderboard report
Emotion Recognition in Conversation IEMOCAP SACL-LSTM Weighted-F1 69.22 #23 of 59 Archive leaderboard report
Emotion Recognition in Conversation IEMOCAP-4 SACL-LSTM Accuracy 80.70 #7 of 8 Archive leaderboard report
Emotion Recognition in Conversation IEMOCAP-4 SACL-LSTM Weighted F1 80.74 #7 of 8 Archive leaderboard report
Emotion Recognition in Conversation MELD SACL-LSTM (one seed) Accuracy 67.89 #13 of 68 Archive leaderboard report
Emotion Recognition in Conversation MELD SACL-LSTM (one seed) Weighted-F1 66.86 #13 of 68 Archive leaderboard report
Emotion Recognition in Conversation MELD SACL-LSTM Accuracy 67.51 #22 of 68 Archive leaderboard report
Emotion Recognition in Conversation MELD SACL-LSTM Weighted-F1 66.45 #22 of 68 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections