Model robustness indicates a model’s capability to generalize well on unforeseen distributional shifts, including data corruptions and adversarial attacks. Data augmentation is one of the most prevalent and effective ways to enhance robustness. Despite the great success of the diverse augmentations in different fields, a unified theoretical understanding of their efficacy in improving model robustness is lacking. We theoretically reveal a general condition for label-preserving augmentations to bring robustness to diverse distribution shifts through the lens of flat minima and generalization bound, which de facto turns out to be strongly correlated with robustness against different distribution shifts in practice. Unlike most earlier works, our theoretical framework accommodates all the label-preserving augmentations and is not limited to particular distribution shifts. We substantiate our theories through different simulations on the existing common corruption and adversarial robustness benchmarks based on the CIFAR and ImageNet datasets.

Flat minima, known to enhance generalization and robustness in supervised learning, remain largely unexplored in generative models. In this work, we systematically investigate the role of loss surface flatness in generative models, both theoretically and empirically, with a particular focus on diffusion models. We establish a theoretical claim that flatter minima improve robustness against perturbations in target prior distributions, leading to benefits such as reduced exposure bias -- where errors in noise estimation accumulate over iterations -- and significantly improved resilience to model quantization, preserving generative performance even under strong quantization constraints. We further observe that Sharpness-Aware Minimization (SAM), which explicitly controls the degree of flatness, effectively enhances flatness in diffusion models even surpassing the indirectly promoting flatness methods -- Input Perturbation (IP) which enforces the Lipschitz condition, ensembling-based approach like Stochastic Weight Averaging (SWA) and Exponential Moving Average (EMA) -- are less effective. Through extensive experiments on CIFAR-10, LSUN Tower, and FFHQ, we demonstrate that flat minima in diffusion models indeed improve not only generative performance but also robustness.

Investigating flat minima on loss surfaces in parameter space is well-documented in the supervised learning context, highlighting its advantages for model generalization. However, limited attention has been paid to the reinforcement learning (RL) context, where the impact of flatter reward landscapes in policy parameter space remains largely unexplored. Beyond merely extrapolating from supervised learning, which suggests a link between flat reward landscapes and enhanced generalization, we aim to formally connect the flatness of the reward surface to the robustness of RL models. In policy models where a deep neural network determines actions, flatter reward landscapes in response to parameter perturbations lead to consistent rewards even when actions are perturbed. Moreover, robustness to action perturbations further enhances robustness against other variations, such as changes in state transition probabilities and reward functions. We extensively simulate various RL environments, confirming the consistent benefits of flatter reward landscapes in enhancing the robustness of RL under diverse conditions, including action selection, transition dynamics, and reward functions. The code for these experiments is available at https://github.com/HK-05/flatreward-RRL.

Learning with multiple modalities has recently demonstrated significant gains in many domains by maximizing the shared information across modalities. However, the current approaches strongly rely on high-quality paired datasets, which allow co-training from the paired labels from different modalities. In this context, we raise a pivotal question: Can a model with one modality synergize the training of other models with the different modalities, even without the paired multimodal labels? Our answer is 'Yes'. As a figurative description, we argue that a writer, i.e., a language model, can promote the training of a painter, i.e., a visual model, even without the paired ground truth of text and image. We theoretically argue that a superior representation can be achieved by the synergy between two different modalities without paired supervision. As proofs of concept, we broadly confirm the considerable performance gains from the synergy among visual, language, and audio models. From a theoretical viewpoint, we first establish a mathematical foundation of the synergy between two different modality models, where each one is trained with its own modality. From a practical viewpoint, our work aims to broaden the scope of multimodal learning to encompass the synergistic usage of single-modality models, relieving a strong limitation of paired supervision. The code is available at https://github.com/johnjaejunlee95/synergistic-multimodal.

RAN-agnostic communications can identify intrinsic features of the unknown signal without any prior knowledge, with which incompatible RANs in the same unlicensed band could achieve better coexistence performance than today’s LBT-based coexistence. Blind modulation identification is its key building block, which blindly identifies the modulation type of an incompatible signal without any prior knowledge. Recent blind modulation identification schemes are built upon deep neural networks, which are limited to single-carrier signal recognition thus not pragmatic for identifying spectro-temporal OFDMA signals whose modulation varies with time and frequency. Therefore, this paper proposes RiSi, a semantic segmentation neural network designed to work on OFDMA’s spectrograms, that employs flattened convolutions to better identify the grid-like pattern of OFDMA’s resource blocks. We trained RiSi with a realistic OFDMA dataset including various channel impairments, and achieved the modulation identification accuracy of 86% on average over four modulation types of BPSK, QPSK, 16-QAM, 64-QAM. Then, we enhanced the generalization performance of RiSi by applying domain generalization methods while treating varying FFT size or varying CP length as different domains, showing that thus-generalized RiSi can perform reasonably well with unseen data.

Recently, semantic communications have drawn great attention as the groundbreaking concept surpasses the limited capacity of Shannon’s theory. Specifically, semantic communications are likely to become crucial in realizing visual tasks that demand massive network traffic. Although highly distinctive forms of visual semantics exist for computer vision tasks, a thorough investigation of what visual semantics can be transmitted in time and which one is required for completing different visual tasks has not yet been reported. To this end, we first scrutinize the achievable throughput in transmitting existing visual semantics through the limited wireless communication bandwidth. In addition, we further demonstrate the resulting performance of various visual tasks for each visual semantic. Based on the empirical testing, we suggest a task-adaptive selection of visual semantics is crucial for real-time semantic communications for visual tasks, where we transmit basic semantics (e.g., objects in the given image) for simple visual tasks, such as classification, and richer semantics (e.g., scene graphs) for complex tasks, such as image regeneration. To further improve transmission efficiency, we suggest a filtering method for scene graphs, which drops redundant information in the scene graph, thus allowing the sending of essential semantics for completing the given task.We confirm the efficacy of our task-adaptive semantic communication approach through extensive simulations in wireless channels, showing more than 45 times larger throughput over a naive transmission of original data. Our work can be reproduced at the following source codes: https://github.com/jhpark2024/jhpark.github.io.

Federated learning (FL) enables decentralized training while preserving data privacy, yet existing FL benchmarks address relatively simple classification tasks, where each sample is annotated with a one-hot label. However, little attention has been paid to demonstrating an FL benchmark that handles complicated semantics, where each sample encompasses diverse semantic information, such as relations between objects. Because the existing benchmarks are designed to distribute data in a narrow view of a single semantic, managing the complicated semantic heterogeneity across clients when formalizing FL benchmarks is non-trivial. In this paper, we propose a benchmark process to establish an FL benchmark with controllable semantic heterogeneity across clients: two key steps are (i) data clustering with semantics and (ii) data distributing via controllable semantic heterogeneity across clients. As a proof of concept, we construct a federated PSG benchmark, demonstrating the efficacy of the existing PSG methods in an FL setting with controllable semantic heterogeneity of scene graphs. We also present the effectiveness of our benchmark by applying robust federated learning algorithms to data heterogeneity to show increased performance. To our knowledge, this is the first benchmark framework that enables federated learning and its evaluation for multi-semantic vision tasks under the controlled semantic heterogeneity. Our code is available at https://github.com/Seung-B/FL-PSG .

Meta-learning, which pursues an effective initialization model, has emerged as a promising approach to handling unseen tasks. However, a limitation remains to be evident when a meta-learner tries to encompass a wide range of task distribution, e.g., learning across distinctive datasets or domains. Recently, a group of works has attempted to employ multiple model initializations to cover widely-ranging tasks, but they are limited in adaptively expanding initializations. We introduce XB-MAML, which learns expandable basis parameters, where they are linearly combined to form an effective initialization to a given task. XB-MAML observes the discrepancy between the vector space spanned by the basis and fine-tuned parameters to decide whether to expand the basis. Our method surpasses the existing works in the multi-domain meta-learning benchmarks and opens up new chances of meta-learning for obtaining the diverse inductive bias that can be combined to stretch toward the effective initialization for diverse unseen tasks.

Albeit the success of federated learning (FL) in decentralized training, bolstering the generalization of models by overcoming heterogeneity across clients still remains a huge challenge. To aim at improved generalization of FL, a group of recent works pursues flatter minima of models by employing sharpness-aware minimization in the local training at the client side. However, we observe that the global model, i.e., the aggregated model, does not lie on flat minima of the global objective, even with the effort of flatness searching in local training, which we define as flatness discrepancy. By rethinking and theoretically analyzing flatness searching in FL through the lens of the discrepancy problem, we propose a method called Federated Learning for Global Flatness (FedGF) that explicitly pursues the flatter minima of the global models, leading to the relieved flatness discrepancy and remarkable performance gains in the heterogeneous FL benchmarks.

Few-shot class-incremental learning (FSCIL) aims to learn a classification model for continually accepting novel classes with a few samples. The key of FSCIL is the joint success of the following two training stages: Base training stage to classify base classes and Incremental training stage with sequential learning of novel classes. However, recent efforts show a tendency to focus on one of the stages, or separately design strategies for each stage, so that less effort has been paid to devise a consistent strategy across the consecutive stages. In this paper, we first emphasize the particular aspects of the successful FSCIL algorithm that are worthwhile to consistently pursue during both stages, i.e., intra-class compactness and inter-class separability of the representation, which allows a model to reserve feature space in between current classes for preparing the acceptance of novel classes in the future. To achieve these aspects, we propose a mixup-based FSCIL method called MICS, which theoretically guarantees to enlarge the thickness of the margin space between different classes, leading to outstanding performance on the existing benchmarks. Code is available at https://github.com/solangii/MICS.

One of the daunting challenges in federated learning (FL) is the heterogeneity across clients that hinders the successful federation of a global model. When the heterogeneity becomes worse, personalized federated learning (PFL) pursues to detour the hardship of capturing the commonality across clients by allowing the personalization of models built upon the federation. In the scope of PFL for visual models, on the contrary, the recent effort for aggregating an effective global representation rather than chasing further personalization draws great attention. Along the same lines, we aim to train a large-margin global representation with a strong generalization across clients by adopting the meta-learning framework and margin-based loss, which are widely accepted to be effective in handling multiple visual tasks. Our method called MetaVers achieves state-of-the-art accuracies for the PFL benchmarks with the CIFAR-10, CIFAR-100, and CINIC-10 datasets while showing robustness against data reconstruction attacks. Noteworthy, the versatile representation of MetaVers exhibits a strong generalization when tested on new clients with novel classes. Code is available at https://github.com/eepLearning/MetaVers.

Handling out-of-distribution samples is a long-lasting challenge for deep visual models. In particular, domain generalization (DG) is one of the most relevant tasks that aims to train a model with a generalization capability on novel domains. Most existing DG approaches share the same philosophy to minimize the discrepancy between domains by finding the domain-invariant representations. On the contrary, our proposed method called POEM acquires a strong DG capability by learning domain-invariant and domain-specific representations and polarizing them. Specifically, POEM co-trains category-classifying and domain-classifying embeddings while regularizing them to be orthogonal via minimizing the cosine-similarity between their features, i.e., the polarization of embeddings. The clear separation of embeddings suppresses domain-specific features in the domain-invariant embeddings. The concept of POEM shows a unique direction to enhance the domain robustness of representations that brings considerable and consistent performance gains when combined with existing DG methods. Extensive simulation results in popular DG benchmarks with the PACS, VLCS, OfficeHome, TerraInc, and DomainNet datasets show that POEM indeed facilitates the category-classifying embedding to be more domain-invariant.

Learning novel concepts while preserving prior knowledge is a long-standing challenge in machine learning. The challenge gets greater when a novel task is given with only a few labeled examples, a problem known as incremental few-shot learning. We propose XtarNet, which learns to extract task-adaptive representation (TAR) for facilitating incremental few-shot learning. The method utilizes a backbone network pretrained on a set of base categories while also employing additional modules that are meta-trained across episodes. Given a new task, the novel feature extracted from the meta-trained modules is mixed with the base feature obtained from the pretrained model. The process of combining two different features provides TAR and is also controlled by meta-trained modules. The TAR contains effective information for classifying both novel and base categories. The base and novel classifiers quickly adapt to a given task by utilizing the TAR. Experiments on standard image datasets indicate that XtarNet achieves state-of-the-art incremental few-shot learning performance. The concept of TAR can also be used in conjunction with existing incremental few-shot learning methods; extensive simulation results in fact show that applying TAR enhances the known methods significantly.

Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning. Here, employing a meta-learning strategy with episode-based training, a network and a set of per-class reference vectors are learned across widely varying tasks. At the same time, for every episode, features in the embedding space are linearly projected into a new space as a form of quick task-specific conditioning. The training loss is obtained based on a distance metric between the query and the reference vectors in the projection space. Excellent generalization results in this way. When tested on the Omniglot, miniImageNet and tieredImageNet datasets, we obtain state of the art classification accuracies under various few-shot scenarios.

This paper investigates interplay among storage overhead, bandwidth requirement, and security constraint in distributed storage. In the model used in our analysis, storage nodes are dispersed in multiple clusters. When a node fails, necessary content gets restored by downloading data from different nodes that may possibly be in other clusters. The bandwidth required for transferring data for node repair is assumed more scarce for cluster-to-cluster links than the links connecting intra-cluster nodes. Eavesdropping takes place on links across clusters only, and a fraction of the total number of clusters is assumed compromised. When a cluster is compromised, any repair traffic going in and out of it is eavesdropped. For this clustered model with eavesdroppers, we analyze the security of distributed storage systems (DSSs) and provide guidelines on designing system solutions for securing the data. First, under the setting of functional repair, we derive a general upper bound on the secrecy capacity, the maximum data size that can be stored in DSSs with perfect secrecy. In the practically important bandwidth-limited regime where the node storage size is equal to the repair bandwidth, the upper bound is shown to be achievable through proposed code constructions. Moreover, we obtain a closed-form expression for the required system resources-node storage size and repair bandwidth-to store a given amount of data with perfect secrecy. Second, we investigate the behavior of secrecy capacity as the number of compromised clusters increases. According to our mathematical analysis, the secrecy capacity decreases as a quadratic function until the number of compromised clusters reaches a certain threshold. Finally, based on the fundamental relationship between the system resources and the secrecy capacity, we provide a guideline on balancing intra- and cross-cluster repair bandwidths depending on the given system security level.

This paper considers the security issue of practical distributed storage systems (DSSs) which consist of multiple clusters of storage nodes. Noticing that actual storage nodes constituting a DSS are distributed in multiple clusters, two novel eavesdropper models - the node-restricted model and the cluster-restricted model - are suggested which reflect the clustered nature of DSSs. In the node-restricted model, an eavesdropper cannot access the individual nodes, but can eavesdrop incoming/outgoing data for Lccompromised clusters. In the cluster-restricted model, an eavesdropper can access a total of l individual nodes but the number of accessible clusters is limited to Lc. We provide an upper bound on the securely storable data for each model, while a specific network coding scheme which achieves the upper bound is obtained for the node-restricted model, given some mild condition on the node storage size.

A new system model reflecting the clustered structure of distributed storage is suggested to investigate interplay between storage overhead and repair bandwidth as storage node failures occur. Large data centers with multiple racks/disks or local networks of storage devices (e.g., sensor network) are good applications of the suggested clustered model. In realistic scenarios involving clustered storage structures, repairing storage nodes using intact nodes residing in other clusters are more bandwidth consuming than restoring nodes based on information from intra-cluster nodes. Therefore, it is important to differentiate between intra-cluster repair bandwidth and cross-cluster repair bandwidth in modeling distributed storage. Capacity of the suggested model is obtained as a function of fundamental resources of distributed storage systems, namely, node storage capacity, intra-cluster repair bandwidth, and cross-cluster repair bandwidth. The capacity is shown to be asymptotically equivalent to a monotonic decreasing function of number of clusters, as the number of storage nodes increases without bound. Based on the capacity expression, feasible sets of required resources which enable reliable storage are obtained in a closed-form solution. Specifically, it is shown that the cross-cluster traffic can be minimized to zero (i.e., intra-cluster local repair becomes possible) by allowing extra resources on storage capacity and intra-cluster repair bandwidth, according to the law specified in the closed form. The network coding schemes with zero cross-cluster traffic are defined as intra-cluster repairable codes, which are shown to be a class of the previously developed locally repairable codes.

Pilot reuse in multi-cell massive multi-input multi-output (MIMO) system is investigated where user groups with different priorities exist. Recent investigation on pilot reuse has revealed that when the ratio of the coherent time interval to the number of users is reasonably high, it is beneficial not to fully reuse pilots from interfering cells. This work finds the optimum pilot assignment strategy that would maximize the weighted sum rate (WSR) given the user groups with different priorities. A closed-form solution for the optimal pilot assignment is derived and is shown to make intuitive sense. Performance comparison shows that under wide range of channel conditions, the optimal pilot assignment that uses extra set of pilots achieves better WSR performance than conventional full pilot reuse.

Pilot contamination, caused by the reuse of pilots among interfering cells, remains a significant obstacle that limits the performance of massive multi-input multi-output antenna systems. To handle this problem, less aggressive reuse of pilots involving allocation of additional pilots for interfering users is closely examined in this paper. Hierarchical pilot reuse methods are proposed, which effectively mitigate pilot contamination and increase the net throughput of the system. Among the suggested hierarchical pilot reuse schemes, the optimal way of assigning pilots to different users is obtained in a closed-form solution, which maximizes the net sum-rate in a given coherence time. Simulation results confirm that when the ratio of the channel coherence time to the number of users in each cell is sufficiently large, less aggressive reuse of pilots yields significant performance advantage relative to the case, where all cells reuse the same pilot set.

Two-dimensional (2D) cyclic codes are presented which correct any single occurrence of known 2D error patterns within a 2D array of bits. Applications for this type of codes include storage and display devices. The code construction begins with a generation of distinct syndrome sets for all targeted 2D error patterns. A method to refine the syndrome sets is then presented for making each syndrome set to contain distinct members, thereby guaranteeing full correction capability for the given list of known error patterns. Using an example construction, the effectiveness of the proposed coding approach is demonstrated versus the maximum-distance-separable (MDS) random-error-correcting code and known 2D burst-correcting codes for a 2D intersymbol interference (ISI) channel that yields a few dominant, but relatively large error patterns.

This paper considers error-correcting codes designed to correct a finite set of known two-dimensional (2D) error patterns that can occur in a 2D array of bits. Obvious applications for this type of codes include storage and display devices. The specific codes designed in this paper are cyclic codes that can correct any single occurrences of dominant known error patterns that can occur anywhere in the 2D array. As example codes, rate-0.994 codes are constructed which target eight known 2D error patterns in a 63 × 63 bit array.