Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks

While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source datasets or introducing regularization terms such as contrastive loss. However, these methods require auxiliary source information (e.g., source labels or datasets) or heavy additional computations. In this paper, we propose a simple method called adaptive random feature regularization (AdaRand). AdaRand helps the feature extractors of training models to adaptively change the distribution of feature vectors for downstream classification tasks without auxiliary source information and with reasonable computation costs. To this end, AdaRand minimizes the gap between feature vectors and random reference vectors that are sampled from class conditional Gaussian distributions. Furthermore, AdaRand dynamically updates the conditional distribution to follow the currently updated feature extractors and balance the distance between classes in feature spaces. Our experiments show that AdaRand outperforms the other fine-tuning regularization, which requires auxiliary source information and heavy computation costs.

Partial Search in a Frozen Network is Enough to Find a Strong Lottery Ticket

Randomly initialized dense networks contain subnetworks that achieve high accuracy without weight learning -- strong lottery tickets (SLTs). Recently, Gadhikar et al. (2023) demonstrated theoretically and experimentally that SLTs can also be found within a randomly pruned source network, thus reducing the SLT search space. However, this limits the search to SLTs that are even sparser than the source, leading to worse accuracy due to unintentionally high sparsity. This paper proposes a method that reduces the SLT search space by an arbitrary ratio that is independent of the desired SLT sparsity. A random subset of the initial weights is excluded from the search space by freezing it -- i.e., by either permanently pruning them or locking them as a fixed part of the SLT. Indeed, the SLT existence in such a reduced search space is theoretically guaranteed by our subset-sum approximation with randomly frozen variables. In addition to reducing search space, the random freezing pattern can also be exploited to reduce model size in inference. Furthermore, experimental results show that the proposed method finds SLTs with better accuracy and model size trade-off than the SLTs obtained from dense or randomly pruned source networks. In particular, the SLT found in a frozen graph neural network achieves higher accuracy than its weight trained counterpart while reducing model size by $40.3\times$.

Regularizing Neural Networks with Meta-Learning Generative Models

This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative models as an additional dataset for classification with small dataset settings. A key challenge of generative data augmentation is that the synthetic data contain uninformative samples that degrade accuracy. This is because the synthetic samples do not perfectly represent class categories in real data and uniform sampling does not necessarily provide useful samples for tasks. In this paper, we present a novel strategy for generative data augmentation called meta generative regularization (MGR). To avoid the degradation of generative data augmentation, MGR utilizes synthetic samples in the regularization term for feature extractors instead of in the loss function, e.g., cross-entropy. These synthetic samples are dynamically determined to minimize the validation losses through meta-learning. We observed that MGR can avoid the performance degradation of na\"ive generative data augmentation and boost the baselines. Experiments on six datasets showed that MGR is effective particularly when datasets are smaller and stably outperforms baselines.

Revisiting Permutation Symmetry for Merging Models between Different Datasets

Model merging is a new approach to creating a new model by combining the weights of different trained models. Previous studies report that model merging works well for models trained on a single dataset with different random seeds, while model merging between different datasets is difficult. Merging knowledge from different datasets has practical significance, but it has not been well investigated. In this paper, we investigate the properties of merging models between different datasets. Through theoretical and empirical analyses, we find that the accuracy of the merged model decreases more significantly as the datasets diverge more and that the different loss landscapes for each dataset make model merging between different datasets difficult. We also show that merged models require datasets for merging in order to achieve a high accuracy. Furthermore, we show that condensed datasets created by dataset condensation can be used as substitutes for the original datasets when merging models. We conduct experiments for model merging between different datasets. When merging between MNIST and Fashion- MNIST models, the accuracy significantly improves by 28% using the dataset and 25% using the condensed dataset compared with not using the dataset.

Transferring Learning Trajectories of Neural Networks

Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated training runs, such as model ensemble or knowledge distillation. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of "transferring" a given learning trajectory from one initial parameter to another one, called learning transfer problem, and derive the first algorithm to approximately solve it by matching gradients successively along the trajectory via permutation symmetry. We empirically show that the transferred parameters achieve non-trivial accuracy before any direct training. Also, we analyze the loss landscape property of the transferred parameters, especially from a viewpoint of mode connectivity.

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks

Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized NNs can easily overfit to such small dataset. Previous work (e.g. MAML by Finn et al. 2017) tackles this challenge by meta-learning, which learns how to learn from a few data by using various tasks. On the other hand, one conventional approach to avoid overfitting is restricting hypothesis spaces by endowing sparse NN structures like convolution layers in computer vision. However, although such manually-designed sparse structures are sample-efficient for sufficiently large datasets, they are still insufficient for few-shot learning. Then the following questions naturally arise: (1) Can we find sparse structures effective for few-shot learning by meta-learning? (2) What benefits will it bring in terms of meta-generalization? In this work, we propose a novel meta-learning approach, called Meta-ticket, to find optimal sparse subnetworks for few-shot learning within randomly initialized NNs. We empirically validated that Meta-ticket successfully discover sparse subnetworks that can learn specialized features for each given task. Due to this task-wise adaptation ability, Meta-ticket achieves superior meta-generalization compared to MAML-based methods especially with large NNs.

Transfer Learning with Pre-trained Conditional Generative Models

Transfer learning is crucial in training deep neural networks on new target tasks. Current transfer learning methods generally assume at least one of (i) source and target task label spaces must overlap, (ii) source datasets are available, and (iii) target network architectures are consistent with source ones. However, these all assumptions are difficult to hold in practical settings because the target task rarely has the same labels as the source task, the source dataset access is restricted due to licensing and storage costs, and the target architecture is often specialized to each task. To transfer source knowledge without these assumptions, we propose a transfer learning method that uses deep generative models and is composed of the following two stages: pseudo pre-training (PP) and pseudo semi-supervised learning (P-SSL). PP trains a target architecture with a synthesized dataset by using conditional source generative models. P-SSL applies SSL algorithms to labeled target data and unlabeled pseudo samples, which are generated by cascading the source classifier and generative models to condition them with target samples. Our experimental results indicate that our method can outperform baselines of scratch training and knowledge distillation.

Pruning Randomly Initialized Neural Networks with Iterative Randomization

Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that only pruning the weights can achieve remarkable performance instead of optimizing the weight values. However, to achieve the same level of performance as the weight optimization, the pruning approach requires more parameters in the networks before pruning and thus more memory space. To overcome this parameter inefficiency, we introduce a novel framework to prune randomly initialized neural networks with iteratively randomizing weight values (IteRand). Theoretically, we prove an approximation theorem in our framework, which indicates that the randomizing operations are provably effective to reduce the required number of the parameters. We also empirically demonstrate the parameter efficiency in multiple experiments on CIFAR-10 and ImageNet.