Sparse Neural Networks (SNNs) have received voluminous attention predominantly due to growing computational and memory footprints of consistently exploding parameter count in large-scale models. Similar to their dense counterparts, recent SNNs generalize just as well and are equipped with numerous favorable benefits (e.g., low complexity, high scalability, and robustness), sometimes even better than the original dense networks. As research effort is focused on developing increasingly sophisticated sparse algorithms, it is startling that a comprehensive benchmark to evaluate the effectiveness of these algorithms has been highly overlooked. In absence of a carefully crafted evaluation benchmark, most if not all, sparse algorithms are evaluated against fairly simple and naive tasks (eg. CIFAR-10/100, ImageNet, GLUE, etc.), which can potentially camouflage many advantages as well unexpected predicaments of SNNs. In pursuit of a more general evaluation and unveiling the true potential of sparse algorithms, we introduce “Sparsity May Cry” Benchmark (SMC-Bench), a collection of carefully-curated 4 diverse tasks with 10 datasets, that accounts for capturing a wide range of domain-specific and sophisticated knowledge. Our systemic evaluation of the most representative sparse algorithms reveals an important obscured observation: the state-of-the-art magnitude- and/or gradient-based sparse algorithms seemingly fail to perform on SMC-Bench when applied out-of-the-box, sometimes at significantly trivial sparsity as low as 5%. The observations seek the immediate attention of the sparsity research community to reconsider the highly proclaimed benefits of SNNs. We further conduct a thorough investigation into the reasons for the failure of common SNNs. Our analysis points out that such failure is intimately related to the “lazy regime” of large model training, which hints us with stronger pruning recipes that alleviate the failure on SMC-Bench (though still more or less suffering). By incorporating these well-thought and diverse tasks, SMC-Bench is designed to favor and encourage the development of more scalable and generalizable sparse algorithms. We open-source SMC-Bench to assist researchers in building next-generation sparse algorithms that scale and generalize: https://github.com/VITA-Group/SMC-Bench.

Incorporating second-order gradient information (curvature) into optimization can dramatically reduce the number of iterations required to train machine learning models. In natural gradient descent, such information comes from the Fisher information matrix which yields a number of desirable properties. As exact natural gradient updates are intractable for large models, successful methods such as KFAC and sequels approximate the Fisher in a structured form that can easily be inverted. However, this requires model/layer-specific tensor algebra and certain approximations that are often difficult to justify. Here, we use ideas from Legendre-Fenchel duality to learn a direct and efficiently evaluated model for the product of the inverse Fisher with any vector, in an online manner, leading to natural gradient steps that get progressively more accurate over time despite noisy gradients. We prove that the resulting “Fisher-Legendre” (FishLeg) optimizer converges to a (global) minimum of non-convex functions satisfying the PL condition, which applies in particular to deep linear networks. On standard auto-encoder benchmarks, we show empirically that FishLeg outperforms standard first-order optimization methods, and performs on par with or better than other second-order methods, especially when using small batches. Thanks to its generality, we expect our approach to facilitate the handling of a variety neural network layers in future work.

Recent empirical studies on domain generalization (DG) have shown that DG algorithms that perform well on some distribution shifts fail on others, and no state-of-the-art DG algorithm performs consistently well on all shifts. Moreover, real-world data often has multiple distribution shifts over different attributes; hence we introduce multi-attribute distribution shift datasets and find that the accuracy of existing DG algorithms falls even further. To explain these results, we provide a formal characterization of generalization under multi-attribute shifts using a canonical causal graph. Based on the relationship between spurious attributes and the classification label, we obtain realizations of the canonical causal graph that characterize common distribution shifts and show that each shift entails different independence constraints over observed variables. As a result, we prove that any algorithm based on a single, fixed constraint cannot work well across all shifts, providing theoretical evidence for mixed empirical results on DG algorithms. Based on this insight, we develop Causally Adaptive Constraint Minimization (CACM), an algorithm that uses knowledge about the data-generating process to adaptively identify and apply the correct independence constraints for regularization. Results on fully synthetic, MNIST, small NORB, and Waterbirds datasets, covering binary and multi-valued attributes and labels, show that adaptive dataset-dependent constraints lead to the highest accuracy on unseen domains whereas incorrect constraints fail to do so. Our results demonstrate the importance of modeling the causal relationships inherent in the data-generating process.

Distillation-aware Network Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best performance and/or efficiency when distilling the knowledge from a given teacher model. Previous DaNAS methods have mostly tackled the search for the network architecture for fixed source/target tasks and the teacher, which are not generalized well on a new task, thus need to perform a costly search for any new combination of the domains and the teachers. For standard NAS tasks without KD, meta-learning-based computationally efficient NAS methods have been proposed, which learn the generalized search process over multiple tasks and transfer the knowledge obtained over those tasks to a new task. However, since they assume learning from scratch without KD from a teacher, they might not be ideal for DaNAS scenarios, which could significantly affect the final performances of the architectures obtained from the search. To eliminate the excessive computational cost of DaNAS methods and the sub-optimality of rapid NASmethods, we propose a distillation-aware meta accuracy prediction model, DaSS (Distillation-aware Student Search), which can predict a given architecture’s final performances on a dataset when performing KD with a given teacher, without having actually to train it on the target task. The experimental results demonstrate that our proposed meta-prediction model successfully generalizes to multiple unseen datasets for DaNAS tasks, largely outperforming existing meta-NAS methods and rapid NAS baselines. Code is available at https://github.com/CownowAn/DaSS.

Neural Representations have recently been shown to effectively reconstruct a wide range of signals from 3D meshes and shapes to images and videos. We show that, when adapted correctly, neural representations can be used to directly represent the weights of a pre-trained convolutional neural network, resulting in a Neural Representation for Neural Networks (NeRN). Inspired by coordinate inputs of previous neural representation methods, we assign a coordinate to each convolutional kernel in our network based on its position in the architecture, and optimize a predictor network to map coordinates to their corresponding weights. Similarly to the spatial smoothness of visual scenes, we show that incorporating a smoothness constraint over the original network's weights aids NeRN towards a better reconstruction. In addition, since slight perturbations in pre-trained model weights can result in a considerable accuracy loss, we employ techniques from the field of knowledge distillation to stabilize the learning process. We demonstrate the effectiveness of NeRN in reconstructing widely used architectures on CIFAR-10, CIFAR-100, and ImageNet. Finally, we present two applications using NeRN, demonstrating the capabilities of the learned representations.

Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain. It does not require access to both the source-domain data and the predictor parameters, thus addressing the data privacy and portability issues of standard domain adaptation methods. Existing DABP approaches mostly rely on knowledge distillation (KD) from the black-box predictor, i.e., training the model with its noisy target-domain predictions, which however inevitably introduces the confirmation bias accumulated from the prediction noises and leads to degrading performance. To mitigate such bias, we propose a new strategy, \textit{divide-to-adapt}, that purifies cross-domain knowledge distillation by proper domain division. This is inspired by an observation we make for the first time in domain adaptation: the target domain usually contains easy-to-adapt and hard-to-adapt samples that have different levels of domain discrepancy w.r.t. the source domain, and deep models tend to fit easy-to-adapt samples first. Leveraging easy-to-adapt samples with less noise can help KD alleviate the negative effect of prediction noises from black-box predictors. In this sense, the target domain can be divided into an easy-to-adapt subdomain with less noise and a hard-to-adapt subdomain at the early stage of training. Then the adaptation is achieved by semi-supervised learning. We further reduce distribution discrepancy between subdomains and develop weak-strong augmentation strategy to filter the predictor errors progressively. As such, our method is a simple yet effective solution to reduce error accumulation in cross-domain knowledge distillation for DABP. Moreover, we prove that the target error of DABP is bounded by the noise ratio of two subdomains, i.e., the confirmation bias, which provides the theoretical justifications for our method. Extensive experiments demonstrate our method achieves state of the art on all DABP benchmarks, outperforming the existing best approach by 7.0\% on VisDA-17, and is even comparable with the standard domain adaptation methods that use the source-domain data.

Limited progress has been made in continual unsupervised learning of representations, especially in reusing, expanding, and continually disentangling learned semantic factors across data environments. We argue that this is because existing approaches treat continually-arrived data independently, without considering how they are related based on the underlying semantic factors. We address this by a new generative model describing a topologically-connected mixture of spike-and-slab distributions in the latent space, learned end-to-end in a continual fashion via principled variational inference. The learned mixture is able to automatically discover the active semantic factors underlying each data environment and to accumulate their relational structure based on that. This distilled knowledge of different data environments can further be used for generative replay and guiding continual disentangling of new semantic factors. We tested the presented method on a split version of 3DShapes to provide the first quantitative disentanglement evaluation of continually learned representations, and further demonstrated its ability to continually disentangle new representations in benchmark datasets.