Continual Vision-Language Representaion Learning with Off-Diagonal Information

Zixuan Ni, Longhui Wei, Siliang Tang, Yueting Zhuang, Qi Tian

Keywords: representation learning, continual learning

TL;DR: we explore the feasibility of training CLIP model continuously through streaming data and find the reason about cognitive disorder in continual CLIP training and produce a new framework Mod-x to alleviate model's cognitive disorder.

Abstract: Multimodal pre-trained methods with a contrastive learning framework (like CLIP) have recently achieved consistent advantages on various cross-model downstream tasks. However, they usually require a large amount of image-text samples and a vast computing budget for training, which makes the re-training process expensive while the training data is collected continuously (the phenomenon is widespread in real scenarios). In this paper, we discuss the feasibility of continuously training CLIP models based on discrete streaming data. We find that the multimodal retrieval performance of the CLIP in a continual training setting is significantly lower than that in a joint training setting. We name this phenomenon Cognitive Disorder(CD). By tracking the directional changes of the representation vectors in the continuously updated CLIP model, we explore and summarize the spatial variation of the modal encoders within the CLIP: Intra-modal Rotation and Inter-modal Deviation. Intra-modal Rotation means that the vision and language representation space in the CLIP is rotating greatly around the center of a high-dimensional unit sphere during continual training, accompanied by a relatively small change in the topology of the representation space. Inter-modal deviation happens when the vision and language's intra-modal rotation is unsynchronized. Moreover, we empirically and theoretically demonstrate how intra-modal rotation and inter-modal deviation lead to CD. In order to alleviate CD in continual CLIP training, we propose a new continual training framework Mod-X: Maintain off-diagonal information-matrix. By selectively aligning the off-diagonal information distribution of contrastive matrixes, the Mod-X helps the model not only better fits the newly trained data domain but also maintains the multimodal cognitive ability on the old data domain during the continual large-scale training (Section \ref{experiments}).

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning