Flat Posterior Does Matter For Bayesian Transfer Learning

The large-scale pre-trained neural network has achieved notable success in enhancing performance for downstream tasks. Another promising approach for generalization is Bayesian Neural Network (BNN), which integrates Bayesian methods into neural network architectures, offering advantages such as Bayesian Model averaging (BMA) and uncertainty quantification. Despite these benefits, transfer learning for BNNs has not been widely investigated and shows limited improvement. We hypothesize that this issue arises from the inability to find flat minima, which is crucial for generalization performance. To address this, we evaluate the sharpness of BNNs in various settings, revealing their insufficiency in seeking flat minima and the influence of flatness on BMA performance. Therefore, we propose Sharpness-aware Bayesian Model Averaging (SA-BMA), a Bayesian-fitting flat posterior seeking optimizer integrated with Bayesian transfer learning. SA-BMA calculates the divergence between posteriors in the parameter space, aligning with the nature of BNNs, and serves as a generalized version of existing sharpness-aware optimizers. We validate that SA-BMA improves generalization performance in few-shot classification and distribution shift scenarios by ensuring flatness.

Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners

Few-Shot Class Incremental Learning (FSCIL) is a task that requires a model to learn new classes incrementally without forgetting when only a few samples for each class are given. FSCIL encounters two significant challenges: catastrophic forgetting and overfitting, and these challenges have driven prior studies to primarily rely on shallow models, such as ResNet-18. Even though their limited capacity can mitigate both forgetting and overfitting issues, it leads to inadequate knowledge transfer during few-shot incremental sessions. In this paper, we argue that large models such as vision and language transformers pre-trained on large datasets can be excellent few-shot incremental learners. To this end, we propose a novel FSCIL framework called PriViLege, Pre-trained Vision and Language transformers with prompting functions and knowledge distillation. Our framework effectively addresses the challenges of catastrophic forgetting and overfitting in large models through new pre-trained knowledge tuning (PKT) and two losses: entropy-based divergence loss and semantic knowledge distillation loss. Experimental results show that the proposed PriViLege significantly outperforms the existing state-of-the-art methods with a large margin, e.g., +9.38% in CUB200, +20.58% in CIFAR-100, and +13.36% in miniImageNet. Our implementation code is available at https://github.com/KHU-AGI/PriViLege.

Mitigating the Linguistic Gap with Phonemic Representations for Robust Multilingual Language Understanding

Approaches to improving multilingual language understanding often require multiple languages during the training phase, rely on complicated training techniques, and -- importantly -- struggle with significant performance gaps between high-resource and low-resource languages. We hypothesize that the performance gaps between languages are affected by linguistic gaps between those languages and provide a novel solution for robust multilingual language modeling by employing phonemic representations (specifically, using phonemes as input tokens to LMs rather than subwords). We present quantitative evidence from three cross-lingual tasks that demonstrate the effectiveness of phonemic representation, which is further justified by a theoretical analysis of the cross-lingual performance gap.

Towards Calibrated Robust Fine-Tuning of Vision-Language Models

While fine-tuning unlocks the potential of a pre-trained model for a specific task, it compromises the model's ability to generalize to out-of-distribution (OOD) datasets. To mitigate this, robust fine-tuning aims to ensure performance on OOD datasets as well as on an in-distribution (ID) dataset for which the model is being tuned. However, another criterion for reliable machine learning (ML), confidence calibration, has been overlooked despite its increasing demand for real-world high-stakes ML applications (e.g., autonomous driving and medical diagnosis). For the first time, we raise concerns about the calibration of fine-tuned vision-language models (VLMs) under distribution shift by showing that naive fine-tuning and even state-of-the-art robust fine-tuning methods hurt the calibration of pre-trained VLMs, especially on OOD datasets. To address this issue, we provide a simple approach, called calibrated robust fine-tuning (CaRot), that incentivizes calibration and robustness on both ID and OOD datasets. Empirical results on ImageNet-1K distribution shift evaluation verify the effectiveness of our method.

Leveraging Skill-to-Skill Supervision for Knowledge Tracing

Knowledge tracing plays a pivotal role in intelligent tutoring systems. This task aims to predict the probability of students answering correctly to specific questions. To do so, knowledge tracing systems should trace the knowledge state of the students by utilizing their problem-solving history and knowledge about the problems. Recent advances in knowledge tracing models have enabled better exploitation of problem solving history. However, knowledge about problems has not been studied, as well compared to students' answering histories. Knowledge tracing algorithms that incorporate knowledge directly are important to settings with limited data or cold starts. Therefore, we consider the problem of utilizing skill-to-skill relation to knowledge tracing. In this work, we introduce expert labeled skill-to-skill relationships. Moreover, we also provide novel methods to construct a knowledge-tracing model to leverage human experts' insight regarding relationships between skills. The results of an extensive experimental analysis show that our method outperformed a baseline Transformer model. Furthermore, we found that the extent of our model's superiority was greater in situations with limited data, which allows a smooth cold start of our model.

BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning

With the surge of large-scale pre-trained models (PTMs), fine-tuning these models to numerous downstream tasks becomes a crucial problem. Consequently, parameter efficient transfer learning (PETL) of large models has grasped huge attention. While recent PETL methods showcase impressive performance, they rely on optimistic assumptions: 1) the entire parameter set of a PTM is available, and 2) a sufficiently large memory capacity for the fine-tuning is equipped. However, in most real-world applications, PTMs are served as a black-box API or proprietary software without explicit parameter accessibility. Besides, it is hard to meet a large memory requirement for modern PTMs. In this work, we propose black-box visual prompting (BlackVIP), which efficiently adapts the PTMs without knowledge about model architectures and parameters. BlackVIP has two components; 1) Coordinator and 2) simultaneous perturbation stochastic approximation with gradient correction (SPSA-GC). The Coordinator designs input-dependent image-shaped visual prompts, which improves few-shot adaptation and robustness on distribution/location shift. SPSA-GC efficiently estimates the gradient of a target model to update Coordinator. Extensive experiments on 16 datasets demonstrate that BlackVIP enables robust adaptation to diverse domains without accessing PTMs' parameters, with minimal memory requirements. Code: \url{https://github.com/changdaeoh/BlackVIP}

Causally Disentangled Generative Variational AutoEncoder

We propose a new supervised learning method for Variational AutoEncoder (VAE) which has a causally disentangled representation and achieves the causally disentangled generation (CDG) simultaneously. In this paper, CDG is defined as a generative model able to decode an output precisely according to the causally disentangled representation. We found that the supervised regularization of the encoder is not enough to obtain a generative model with CDG. Consequently, we explore sufficient and necessary conditions for the decoder and the causal effect to achieve CDG. Moreover, we propose a generalized metric measuring how a model is causally disentangled generative. Numerical results with the image and tabular datasets corroborate our arguments.

Sharpness-aware Minimization for Worst Case Optimization

Improvement of worst group performance and generalization performance are core problems of current machine learning. There are diverse efforts to increase performance, such as weight norm penalty and data augmentation, but the improvements are limited. Recently, there have been two promising approaches to increase the worst group performance and generalization performance, respectively. Distributionally robust optimization (DRO) focuses on the worst or hardest group to improve the worst-group performance. Besides, sharpness-aware minimization (SAM) finds the flat minima to increase the generalization ability on an unseen dataset. They show significant performance improvements on the worst-group dataset and unseen dataset, respectively. However, DRO does not guarantee flatness, and SAM does not guarantee the worst group performance improvement. In other words, DRO and SAM may fail to increase the worst group performance when the training and test dataset shift occurs. In this study, we propose a new approach, the sharpness-aware group distributionally robust optimization (SGDRO). SGDRO finds the flat-minima that generalizes well on the worst group dataset. Different from DRO and SAM, SGDRO contributes to improving the generalization ability even the distribution shift occurs. We validate that SGDRO shows the smaller maximum eigenvalue and improved performance in the worst group.

Graph Perceiver IO: A General Architecture for Graph Structured Data

Multimodal machine learning has been widely studied for the development of general intelligence. Recently, the remarkable multimodal algorithms, the Perceiver and Perceiver IO, show competitive results for diverse dataset domains and tasks. However, recent works, Perceiver and Perceiver IO, have focused on heterogeneous modalities, including image, text, and speech, and there are few research works for graph structured datasets. A graph is one of the most generalized dataset structures, and we can represent the other dataset, including images, text, and speech, as graph structured data. A graph has an adjacency matrix different from other dataset domains such as text and image, and it is not trivial to handle the topological information, relational information, and canonical positional information. In this study, we provide a Graph Perceiver IO, the Perceiver IO for the graph structured dataset. We keep the main structure of the Graph Perceiver IO as the Perceiver IO because the Perceiver IO already handles the diverse dataset well, except for the graph structured dataset. The Graph Perceiver IO is a general method, and it can handle diverse datasets such as graph structured data as well as text and images. Comparing the graph neural networks, the Graph Perceiver IO requires a lower complexity, and it can incorporate the local and global information efficiently. We show that Graph Perceiver IO shows competitive results for diverse graph-related tasks, including node classification, graph classification, and link prediction.

Learning Fair Representation via Distributional Contrastive Disentanglement

Learning fair representation is crucial for achieving fairness or debiasing sensitive information. Most existing works rely on adversarial representation learning to inject some invariance into representation. However, adversarial learning methods are known to suffer from relatively unstable training, and this might harm the balance between fairness and predictiveness of representation. We propose a new approach, learning FAir Representation via distributional CONtrastive Variational AutoEncoder (FarconVAE), which induces the latent space to be disentangled into sensitive and nonsensitive parts. We first construct the pair of observations with different sensitive attributes but with the same labels. Then, FarconVAE enforces each non-sensitive latent to be closer, while sensitive latents to be far from each other and also far from the non-sensitive latent by contrasting their distributions. We provide a new type of contrastive loss motivated by Gaussian and Student-t kernels for distributional contrastive learning with theoretical analysis. Besides, we adopt a new swap-reconstruction loss to boost the disentanglement further. FarconVAE shows superior performance on fairness, pretrained model debiasing, and domain generalization tasks from various modalities, including tabular, image, and text.