Learning in Order! A Sequential Strategy to Learn Invariant Features for Multimodal Sentiment Analysis
This work proposes a novel and simple sequential learning strategy to train models on videos and texts for multimodal sentiment analysis. To estimate sentiment polarities on unseen out-of-distribution data, we introduce a multimodal model that is trained either in a single source domain or multiple source domains using our learning strategy. This strategy starts with learning domain invariant features from text, followed by learning sparse domain-agnostic features from videos, assisted by the selected features learned in text. Our experimental results demonstrate that our model achieves significantly better performance than the state-of-the-art approaches on average in both single-source and multi-source settings. Our feature selection procedure favors the features that are independent to each other and are strongly correlated with their polarity labels. To facilitate research on this topic, the source code of this work will be publicly available upon acceptance.
Code (0)
등록된 구현이 없습니다.
Tasks
feature selectionMultimodal Sentiment AnalysisSentiment AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sequential Dual Deep Learning with Shape and Texture Features for Sketch Recognition
Recognizing freehand sketches with high arbitrariness is greatly challenging. Most existing methods either ignore the geometric characteristics or treat sketches as handwritten characters with fixed structural ordering. …
Sketch RecognitionContinual Invariant Risk Minimization
Empirical risk minimization can lead to poor generalization behavior on unseen environments if the learned model does not capture invariant feature representations. Invariant risk minimization (IRM) is a recent proposal …
Continual LearningEnhancing Evolving Domain Generalization through Dynamic Latent Representations
Domain generalization is a critical challenge for machine learning systems. Prior domain generalization methods focus on extracting domain-invariant features across several stationary domains to enable generalization to …
Domain GeneralizationEvolving Domain GeneralizationCPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting
Current methods for multivariate time series forecasting can be classified into channel-dependent and channel-independent models. Channel-dependent models learn cross-channel features but often overfit the channel orderi…
Multivariate Time Series ForecastingPermutation Invariant Learning with High-Dimensional Particle Filters
Sequential learning in deep models often suffers from challenges such as catastrophic forgetting and loss of plasticity, largely due to the permutation dependence of gradient-based algorithms, where the order of training…