With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic samples by solving a bilevel optimization problem. However, current methods face challenges in computational efficiency, particularly with high-resolution data and complex architectures. Recently, knowledge-distillation-based dataset condensation approaches have made this process more computationally feasible. Yet, with the recent developments of generative foundation models, there is now an opportunity to achieve even greater compression, enhance the quality of distilled data, and introduce valuable diversity into the data representation. In this work, we propose a two-stage solution. First, we compress the dataset by selecting only the most informative patches to form a coreset. Next, we leverage a generative foundation model to dynamically expand this compressed set in real-time, enhancing the resolution of these patches and introducing controlled variability to the coreset. Our extensive experiments demonstrate the robustness and efficiency of our approach across a range of dataset distillation benchmarks. We demonstrate a significant improvement of over 10% compared to the state-of-the-art on several large-scale dataset distillation benchmarks. The code will be released soon.

In the field of large language model (LLM)-based proof generation, despite being trained on extensive corpora such as OpenWebMath and Arxiv, these models still exhibit only modest performance on proving tasks of moderate difficulty. We believe that this is partly due to the suboptimal order of each proof data used in training. Published proofs often follow a purely logical order, where each step logically proceeds from the previous steps based on the deductive rules. However, this order aims to facilitate the verification of the proof's soundness, rather than to help people and models learn the discovery process of the proof. In proof generation, we argue that the optimal order for one training data sample occurs when the relevant intermediate supervision for a particular proof step in the proof is always positioned to the left of that proof step. We call such order the intuitively sequential order. We validate our claims using two tasks: intuitionistic propositional logic theorem-proving and digit multiplication. Our experiments verify the order effect and provide support for our explanations. We demonstrate that training is most effective when the proof is in the intuitively sequential order. Moreover, the order effect and the performance gap between models trained on different data orders are substantial -- with an 11 percent improvement in proof success rate observed in the propositional logic theorem-proving task, between models trained on the optimal order compared to the worst order.

Federated learning (FL) provides a promising collaborative framework to build a model from distributed clients, and this work investigates the carbon emission of the FL process. Cloud and edge servers hosting FL clients may exhibit diverse carbon footprints influenced by their geographical locations with varying power sources, offering opportunities to reduce carbon emissions by training local models with adaptive computations and communications. In this paper, we propose FedGreen, a carbon-aware FL approach to efficiently train models by adopting adaptive model sizes shared with clients based on their carbon profiles and locations using ordered dropout as a model compression technique. We theoretically analyze the trade-offs between the produced carbon emissions and the convergence accuracy, considering the carbon intensity discrepancy across countries to choose the parameters optimally. Empirical studies show that FedGreen can substantially reduce the carbon footprints of FL compared to the state-of-the-art while maintaining competitive model accuracy.

The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive datasets into a much smaller yet representative set of synthetic samples. However, traditional dataset distillation approaches often struggle to scale effectively with high-resolution images and more complex architectures due to the limitations in bi-level optimization. Recently, several works have proposed exploiting knowledge distillation with decoupled optimization schemes to scale up dataset distillation. Although these methods effectively address the scalability issue, they rely on extensive image augmentations requiring the storage of soft labels for augmented images. In this paper, we introduce Dataset Distillation using Diffusion Models (D3M) as a novel paradigm for dataset distillation, leveraging recent advancements in generative text-to-image foundation models. Our approach utilizes textual inversion, a technique for fine-tuning text-to-image generative models, to create concise and informative representations for large datasets. By employing these learned text prompts, we can efficiently store and infer new samples for introducing data variability within a fixed memory budget. We show the effectiveness of our method through extensive experiments across various computer vision benchmark datasets with different memory budgets.

Modulation recognition is a fundamental task in communication systems as the accurate identification of modulation schemes is essential for reliable signal processing, interference mitigation for coexistent communication technologies, and network optimization. Incorporating deep learning (DL) models into modulation recognition has demonstrated promising results in various scenarios. However, conventional DL models often fall short in online dynamic contexts, particularly in class incremental scenarios where new modulation schemes are encountered during online deployment. Retraining these models on all previously seen modulation schemes is not only time-consuming but may also not be feasible due to storage limitations. On the other hand, training solely on new modulation schemes often results in catastrophic forgetting of previously learned classes. This issue renders DL-based modulation recognition models inapplicable in real-world scenarios because the dynamic nature of communication systems necessitate the effective adaptability to new modulation schemes. This paper addresses this challenge by evaluating the performance of multiple Incremental Learning (IL) algorithms in dynamic modulation recognition scenarios, comparing them against conventional DL-based modulation recognition. Our results demonstrate that modulation recognition frameworks based on IL effectively prevent catastrophic forgetting, enabling models to perform robustly in dynamic scenarios.

Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its susceptibility to adversarial attacks, especially with the aim of inducing forgetting. In this paper, we introduce "BrainWash," a novel data poisoning method tailored to impose forgetting on a continual learner. By adding the BrainWash noise to a variety of baselines, we demonstrate how a trained continual learner can be induced to forget its previously learned tasks catastrophically, even when using these continual learning baselines. An important feature of our approach is that the attacker requires no access to previous tasks' data and is armed merely with the model's current parameters and the data belonging to the most recent task. Our extensive experiments highlight the efficacy of BrainWash, showcasing degradation in performance across various regularization-based continual learning methods.

The rapid progress of AI, combined with its unprecedented public adoption and the propensity of large neural networks to memorize training data, has given rise to significant data privacy concerns. To address these concerns, machine unlearning has emerged as an essential technique to selectively remove the influence of specific training data points on trained models. In this paper, we approach the machine unlearning problem through the lens of continual learning. Given a trained model and a subset of training data designated to be forgotten (i.e., the "forget set"), we introduce a three-step process, named CovarNav, to facilitate this forgetting. Firstly, we derive a proxy for the model's training data using a model inversion attack. Secondly, we mislabel the forget set by selecting the most probable class that deviates from the actual ground truth. Lastly, we deploy a gradient projection method to minimize the cross-entropy loss on the modified forget set (i.e., learn incorrect labels for this set) while preventing forgetting of the inverted samples. We rigorously evaluate CovarNav on the CIFAR-10 and Vggface2 datasets, comparing our results with recent benchmarks in the field and demonstrating the efficacy of our proposed approach.

We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space. During training, we seek local minima that reside within the subspace spanned by these random models (i.e., `basis' networks). Our framework, PRANC, enables significant compaction of a deep model. The model can be reconstructed using a single scalar `seed,' employed to generate the pseudo-random `basis' networks, together with the learned linear mixture coefficients. In practical applications, PRANC addresses the challenge of efficiently storing and communicating deep models, a common bottleneck in several scenarios, including multi-agent learning, continual learners, federated systems, and edge devices, among others. In this study, we employ PRANC to condense image classification models and compress images by compacting their associated implicit neural networks. PRANC outperforms baselines with a large margin on image classification when compressing a deep model almost $100$ times. Moreover, we show that PRANC enables memory-efficient inference by generating layer-wise weights on the fly. The source code of PRANC is here: \url{https://github.com/UCDvision/PRANC}

Federated learning provides a promising privacy-preserving way for utilizing large-scale private edge data from massive Internet-of-Things (IoT) devices. While existing research extensively studied optimizing the learning process, computing efficiency, and communication overhead, one important and often overlooked aspect is that participants contribute predictive knowledge from their data, impacting the quality of the federated models learned. While FedAvg treats each client equally and assigns weight solely based on the number of samples, the diversity of samples on each client could greatly affect the local update performance and the final aggregated model. In this paper, we propose a novel approach to address this issue by introducing a Weighted Averaging (WeiAvg) framework that emphasizes updates from high-diversity clients and diminishes the influence of those from low-diversity clients. Specifically, we introduced a projection-based approximation method to estimate the diversity of client data, instead of the computation of an entropy. We use the approximation because the locally computed entropy may not be transmitted due to excess privacy risk. Extensive experimental results show that WeiAvg converges faster and achieves higher accuracy than the original FedAvg algorithm and FedProx.

Leveraging machine learning to facilitate the optimization process is an emerging field that holds the promise to bypass the fundamental computational bottleneck caused by classic iterative solvers in critical applications requiring near-real-time optimization. The majority of existing approaches focus on learning data-driven optimizers that lead to fewer iterations in solving an optimization. In this paper, we take a different approach and propose to replace the iterative solvers altogether with a trainable parametric set function, that outputs the optimal arguments/parameters of an optimization problem in a single feed forward. We denote our method as Learning to Optimize the Optimization Process (LOOP). We show the feasibility of learning such parametric (set) functions to solve various classic optimization problems including linear/nonlinear regression, principal component analysis, transport-based coreset, and quadratic programming in supply management applications. In addition, we propose two alternative approaches for learning such parametric functions, with and without a solver in the LOOP. Finally, through various numerical experiments, we show that the trained solvers could be orders of magnitude faster than the classic iterative solvers while providing near optimal solutions.