Searcharxiv⌕ Search

arXiv subjects

Yuichi Tanaka

Publications and source records attributed to Yuichi Tanaka.

At least 19 recordsLinked to original sources

FedLoRD: Personalized Federated Learning based on Low-Rank Structures of Model Parameter Differences

We propose FedLoRD, a personalized federated learning (PFL) method based on the low-rank structure of the differences between the global and personalized model parameters. PFL is a branch of federated learning that aims to learn models tailored to the local data of each client under biased local data distributions. In its local training, each client learns a personalized model by regularizing the difference between its model parameters and the global ones sent from the server. The regularization function needs to be designed with priors on the model parameter difference; however, the existing PFL methods rely on empirical choices (e.g., $\ell_1$- and $\ell_2$-norms), which do not take into account the actual characteristics of the difference. The resulting mismatch of priors can lead to suboptimal personalized models. To address this issue, we propose a PFL method whose regularizer is built on an observed characteristic of the model parameter differences: they are approximately low-rank at every layer. In our method, we first formulate a local training problem with nuclear norm regularization on the layer-wise differences. We further rewrite this problem via the factorized representation of the nuclear norm so that it can be efficiently solved by a plain stochastic gradient descent method. Image classification experiments on three benchmark datasets demonstrate that FedLoRD outperforms several existing PFL methods.

cs.LG↗

Towards Signal Processing In Networks: Multiplierless Block Transforms in Data Plane

In this paper, we propose a signal processing concept, signal processing in networks (SPIN), that executes signal processing tasks directly on programmable switches. Traditionally, signal processing tasks, such as denoising, decomposition, and dimensionality reduction, are performed on edge or cloud servers, i.e., raw streams are transmitted from sensors. This imposes a heavy processing load on edge/cloud servers and requires substantial bandwidth. SPIN addresses this problem by performing signal processing on the forwarding path. As an initial realization of SPIN, we implement a DCT-based block transform on a programmable switch. We redesign its computation using a lifting-based lattice structure, multiplierless approximation, and pipeline partitioning across stages in a programmable switch. We verify at the compiler level that the proposed implementation satisfies the strict hardware constraints of the Intel Tofino2--specifically regarding pipeline stages, packet header vector, and ternary content-addressable memory usage--and therefore enables line-rate processing. We further quantify the per-packet latency of the ingress match-action pipeline. The SPIN-oriented preprocessing adds 46 cycles (approximately 31 ns at 1.5 GHz). The total ingress match-action unit latency is approximately 87 ns, which remains consistent with the low-latency operation targeted by SPIN. Furthermore, we implement the proposed block transform on a BMv2 switch using P4 and evaluate it as preprocessing for in-network machine learning. Experimental results demonstrate that the proposed method improves classification performance over unfiltered baselines.

eess.SP↗

Unrolled Time-Varying Graph Signal Restoration under Spatiotemporal Smoothness Priors

In this paper, we propose restoration methods for time-varying graph signals using deep algorithm unrolling (DAU). Time-varying graph signals, such as signals obtained from sensor networks, are nonuniformly distributed in space and observed as time series. Since these observed signals often contain noise and missing values, their restoration needs to consider both spatial and temporal relationships. Our approach is based on an optimization problem that models signal properties using a spatiotemporal regularizer that combines a Sobolev operator for spatial smoothness and a multi-tap FIR filter for temporal smoothness. We then unroll the iterative conjugate gradient method to solve this problem and learn the regularization parameters and filter coefficients in each iteration. Our method can be applied to supervised batch, supervised online, and unsupervised batch settings to learn these parameters. Experiments on several synthetic and real-world datasets show that the supervised batch method achieves the lowest RMSEs in almost all cases. The supervised online and the unsupervised batch methods outperform the existing methods of their own settings, and are often competitive with the existing batch methods.

eess.SP↗

TDOA-Based Online Target Tracking with Simultaneous Sensor Pairing and Relocation

We propose a target tracking method for mobile sensor networks (MSNs) based on time difference-of-arrival (TDOA). Target tracking using an MSN requires reorganizing sensor pairs and relocating sensor positions to obtain TDOAs with higher quality. Existing studies only consider either one while fixing the other, which may limit the tracking accuracy. We address this limitation by simultaneously solving sensor pairing and relocation. We formulate the problem as a maximization of the determinant of the Fisher information matrix, and decompose the problem into two subproblems to solve them alternately. Sensor pairing is solved by a mixed-integer second-order cone program algorithm, and sensor relocation is solved by majorization-minimization. Experimental results show that the proposed method obtains lower tracking error than existing designs with a practical computation time.

eess.SP↗

Multivariate signal restoration via Multifold Graph Learning

We propose a method for restoring noisy and incomplete multivariate signals by learning multifold graphs. Spatial relationships among channels can be utilized to recover missing values and suppress noise. However, these relationships can vary across frequency components and observation windows while retaining common connectivity patterns. We refer to the graphs associated with individual components and windows as multifold graphs. We model multifold graphs as nonnegative combinations of shared prototype graphs. We formulate signal restoration and multifold graph learning as a joint optimization problem and solve it by alternating optimization. We unroll the resulting algorithm into a neural network with trainable regularization weights, step sizes, and filter coefficients. The network is trained in a self-supervised manner. Synthetic experiments show improved graph estimation accuracy over the compared methods. On real-world weather data, the proposed network achieves competitive completion performance with substantially fewer trainable parameters than a self-attention-based model.

eess.SP↗

Ternary Visible Light Communication Using Event-Based Vision Sensors

This paper proposes a ternary visible light communication method using an event-based vision sensor (EVS) and a liquid crystal display (LCD). The throughput of optical camera communication (OCC) is limited by the frame rates of conventional frame-based cameras, and EVSs are expected to overcome this limitation because their pixels asynchronously trigger events with polarity in response to brightness changes, with a temporal resolution on the order of microseconds. However, existing event-based OCC relies on binary signaling that uses only the presence or absence of events and leaves the polarity unused. The proposed method maps the three brightness transitions (increase, decrease, and no change) to ternary symbols, thereby increasing the information carried per symbol. At the transmitter, the LCD displays a marker in which the transmitted data are encoded; at the receiver, the EVS captures the marker and records the brightness changes as events with positive and negative polarities. To suppress errors caused by the timing mismatch between display updates at the transmitter and demodulation at the receiver, we also propose a demodulation algorithm based on frame-transition detection. Experimental results demonstrate that the proposed method achieves a throughput of 336.5 kbps, approximately 150% higher than that of its binary counterpart.

eess.IV↗

Dynamic Sensor Pairing for TDOA-Based Target Tracking via mixed-integer Second-Order Cone Programming

We propose a sensor pairing method for online target tracking based on time-difference-of-arrival (TDOA) measurements through a sensor network. Existing pairing designs fix active sensor pairs in advance. In online tracking, however, adapting the pairing to the current target estimate maintains a favorable sensor-target geometry around it. We select $K$ pairs at each time step to maximize a Fisher information matrix (FIM) criterion under a communication-degree constraint. The original combinatorial problem is cast as a mixed-integer second-order cone program. We solve it at every time step to obtain a globally optimal pairing. Experiments under various noise settings show that the proposed method obtains the lowest tracking error among the methods under the same communication-degree constraint.

eess.SP↗

Multimodal Signal Restoration with Signed Twofold Graph Learning

We propose a method for jointly learning signed twofold graphs and performing signal restoration on multimodal graph signals. Multimodal signals on sensor networks are commonly modeled under the twofold graph assumption (TGA), which represents spatial structure and inter-modality relations as two separate graphs. Existing TGA-based signal restoration methods, however, either assume the graphs are known or restrict edge weights to be non-negative, preventing them from capturing negative inter-modal correlations. We address both limitations as follows. To learn twofold graphs from noisy and incomplete data, we formulate joint signal restoration and twofold graph learning as MAP estimation under a matrix normal prior, where the spatial and modality graph Laplacians appear directly as precision matrices. The resulting non-convex objective is solved by alternating minimization: The signal is updated via conjugate gradient applied to the arising Sylvester-type linear system; the graphs are updated via primal-dual hybrid gradient (PDHG). To capture negative inter-modal correlations, we estimate the signed structure of the modality graph from the dominant eigenspace of a complementary kernel matrix, which is then used in PDHG to update edge magnitudes. These iterative solvers are then unrolled into a feedforward network, with regularization weights and step sizes as layer-wise trainable parameters. Experiments on synthetic multimodal graph signals and two real-world datasets (Japan meteorological and Beijing air-quality data) confirm that the proposed method outperforms existing baselines across a range of noise levels and missing-data patterns; the learned graphs are also directly validated against the ground-truth graphs on the synthetic datasets.

eess.SP↗

Time-Varying Graph Learning with Constraints on Graph Temporal Variation

We propose a novel framework for learning time-varying graphs from spatiotemporal measurements. Given an appropriate prior on the temporal behavior of signals, our proposed method can estimate time-varying graphs from a small number of available measurements. To achieve this, we introduce three regularization terms in convex optimization problems that constrain the sparseness of temporal variations of the time-varying networks. Moreover, a computationally scalable algorithm is introduced to solve the optimization problem efficiently. The experimental results with synthetic and real datasets (point cloud, temperature, and EEG data) demonstrate that our proposed method outperforms state-of-the-art methods.

eess.SP↗

Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming

Signed graphs are equipped with both positive and negative edge weights, encoding pairwise correlations as well as anti-correlations in data. A balanced signed graph is a signed graph with no cycles containing an odd number of negative edges. Laplacian of a balanced signed graph has eigenvectors that map via a simple linear transform to ones in a corresponding positive graph Laplacian, thus enabling reuse of spectral filtering tools designed for positive graphs. We propose an efficient computation method to learn a balanced signed graph Laplacian directly from data. Specifically, extending a previous linear programming (LP) based sparse inverse covariance estimation method called CLIME, we formulate a new LP problem for each Laplacian column $i$, where the linear constraints restrict weight signs of edges stemming from node $i$, so that nodes of same / different polarities are connected by positive / negative edges. We derive a feasible CLIME parameter $ρ_i$ for each sign-constrained column problem. We solve the LP problem efficiently by tailoring a sparse LP method based on ADMM. We theoretically prove that the row / column updates produce a non-increasing objective sequence, and show that the iterations are terminated in a finite number of steps. Extensive experimental results on synthetic and real-world datasets show that our balanced graph learning method outperforms competing methods and enables reuse of spectral filters, wavelets, and graph neural nets (GNN) constructed for positive graphs.

cs.LG↗

WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures

This paper proposes a neural network for low light image enhancement (LLIE) based on retinex theory to make LLIE robust for various dynamic range scenes. The retinex theory is an image formulation model inspired by a human color perception hypothesis, where a low light image is decomposed into intrinsic color context (i.e., reflectance map) and scene-dependent illumination (i.e., illumination map). Due to non-uniqueness of its decomposition, existing retinex-based LLIE methods often fail to achieve stable decomposition, which lead to over-enhancement. Typically, they are sensitive to the dynamic ranges that vary in different lighting conditions. To tackle this issue, we propose WREN: An LLIE neural network with double U-Net-like structures. WREN consists of two U-Net-like sub-networks. The first network has one encoder and two decoders that decompose an input image into the reflectance and illumination maps. The second network with a customized Transformer block between an encoder and a decoder only enhances the illumination map obtained from the first network: This completely follows the assumption of the retinex theory. Finally, the enhanced illumination map is recombined with the reflectance map. The network is trained end-to-end with a scale-invariant loss function, which gives robustness against the illumination scaling. Numerical results show that our method achieves the state-of-the-art performance across multiple datasets. Our code is available online.

cs.CV↗

Lossy compression of weighted graph adjacency matrices by transform coding

In this paper, we propose a compression framework for weighted graphs in which the graph topology is transmitted losslessly and edge weights are compressed lossily. A challenge in the lossy compression of edge weights is that the underlying relationships between edges are ambiguous. To address this issue, we first transform the unweighted graph into the corresponding line graph, whose nodes represent the edges of the original graph and whose edges encode the relationships between them. The line graph transform allows us to regard edge weights as a graph signal defined on the line graph. Instead of transmitting the edge-weight vector, we first transform it with a graph filter bank on the line graph. Then, quantization and entropy coding are performed on the transformed coefficients of the edge weight vector. In addition to the lossy compression method, we formalize edge smoothness on the line graph and show that it serves as a measure of the difficulty of compression. The proposed smoothness measure can be easily calculated without converting to a line graph. This provides insight into the expected compression performance of a given weighted graph. Experiments on synthetic and real-world data validate the effectiveness of the proposed method by comparing it with existing matrix preprocessing methods.

cs.IT↗

Denoising for Neuromorphic Cameras Based on Graph Spectral Features

Neuromorphic cameras, also known as event-based cameras, can detect changes in the environmental brightness asynchronously and independently for each pixel. They output the brightness changes, i.e., events, as 3-D (2-D pixel coordinates + time) streaming data. While event-based cameras are used in many applications because of their desirable characteristics, e.g., high temporal resolution, low latency, low power consumption, and high dynamic range, their measurements contain considerable noise due to their high sensitivity. In this paper, we propose a denoising method for event-based cameras based on graph spectral features. In the proposed method, we first construct a graph where nodes represent events and edges represent the spatiotemporal distance between the events. To calculate the graph-specified parameter that controls the connectivities of a constructed graph, we utilize the prior on the density of 3-D events. We then calculate the eigenvectors of the graph Laplacian. The obtained eigenvectors are used to extract noiseless events directly. In the calculation of the eigenvectors, we customize the graph Laplacian to reorder its eigenvalues. This allows us to leverage fast eigensolver algorithms instead of the naive eigendecomposition and thereby reduce computational complexity. In experiments on synthetic and real-world event data, we demonstrate that the proposed method effectively removes noise events from the raw events compared to alternative methods.

eess.IV↗

Joint Alignment and Denoising for Event-Based Vision Sensors Using Regret-based Pareto Optimization

This paper proposes a joint alignment and denoising method for event-based vision sensors (EVSs). Existing signal processing methods for EVSs typically perform event alignment (EA) and event denoising (ED) as separate modules. However, this separation creates a dilemma: without ED, EA is biased by noise, whereas without EA, ED struggles to distinguish signal events from noise ones. To address this dilemma, we jointly optimize EA and ED by formulating a bi-objective Pareto optimization problem. Our formulation is built upon a contrast map that counts the number of events localized in each pixel. With a contrast map, we can formulate EA as maximizing its variance and ED as minimizing the variance. We cast these two conflicting problems as a Pareto optimization and use a regret strategy to obtain a solution. Experimental results on denoising and motion estimation demonstrate that our method achieves improvements against alternative ones.

eess.IV↗

Dynamic Sensor Scheduling Based on Node Partitioning of Graphs

This paper proposes a dynamic sensor scheduling method for sensor networks. In sensor network applications, we often need multiple equally-informative node subsets that are activated sequentially to make a sensor network robust against concentrated battery consumption and sensor failures. In addition, quality of these subsets changes dynamically and thus we must adapt those changes. To find those node subsets, we propose a graph node partitioning method based on sampling theory for graph signals. We aim to minimize the average reconstruction error for signals obtained at all node subsets, in contrast to conventional single subset selection. The graph node partitioning problem is formulated as a difference-of-convex (DC) optimization based on a subspace prior of graph signals, and is solved by the proximal DC algorithm. It guarantees convergence to a critical point. To accommodate the online scenario where the signal subspace and optimal partitioning may change over time, we adaptively estimate the signal subspace from historical data and sequentially update the prior for our partitioning method. Numerical experiments on synthetic and real-world sensor network data demonstrate that the proposed method achieves lower average mean squared errors compared to alternative methods.

eess.SP↗

Graph Signal Denoising Using Regularization by Denoising and Its Parameter Estimation

In this paper, we propose an interpretable denoising method for graph signals using regularization by denoising (RED). RED is a technique developed for image restoration that uses an efficient (and sometimes black-box) denoiser in the regularization term of the optimization problem. By using RED, optimization problems can be designed with the explicit use of the denoiser, and the gradient of the regularization term can be easily computed under mild conditions. We adapt RED for denoising of graph signals beyond image processing. We show that many graph signal denoisers, including graph neural networks, theoretically or practically satisfy the conditions for RED. We also study the effectiveness of RED from a graph filter perspective. Furthermore, we propose supervised and unsupervised parameter estimation methods based on deep algorithm unrolling. These methods aim to enhance the algorithm applicability, particularly in the unsupervised setting. Denoising experiments for synthetic and real-world datasets show that our proposed method improves signal denoising accuracy in mean squared error compared to existing graph signal denoising methods.

eess.SP↗

Auditory Attention Decoding without Spatial Information: A Diotic EEG Study

Auditory attention decoding (AAD) identifies the attended speech stream in multi-speaker environments by decoding brain signals such as electroencephalography (EEG). This technology is essential for realizing smart hearing aids that address the cocktail party problem and for facilitating objective audiometry systems. Existing AAD research mainly utilizes dichotic environments where different speech signals are presented to the left and right ears, enabling models to classify directional attention rather than speech content. However, this spatial reliance limits applicability to real-world scenarios, such as the "cocktail party" situation, where speakers overlap or move dynamically. To address this challenge, we propose an AAD framework for diotic environments where identical speech mixtures are presented to both ears, eliminating spatial cues. Our approach maps EEG and speech signals into a shared latent space using independent encoders. We extract speech features using wav2vec 2.0 and encode them with a 2-layer 1D convolutional neural network (CNN), while employing the BrainNetwork architecture for EEG encoding. The model identifies the attended speech by calculating the cosine similarity between EEG and speech representations. We evaluate our method on a diotic EEG dataset and achieve 72.70% accuracy, which is 22.58% higher than the state-of-the-art direction-based AAD method.

eess.SP↗

Algorithm Unrolling-based Denoising of Multimodal Graph Signals

We propose a denoising method for multimodal graph signals by an alternating minimization scheme that sequentially solves signal restoration and graph learning problems. Many complex-structured data, i.e., those on sensor networks, can capture multiple modalities at each measurement point, referred to as modalities. They are also assumed to have an underlying structure or correlations in modality as well as space. Such multimodal data are regarded as graph signals on a twofold graph and they are often corrupted by noise. Furthermore, their spatial/modality relationships are not always given a priori: We need to estimate twofold graphs during a denoising algorithm. In this paper, we consider a signal denoising method on twofold graphs, where graphs are learned simultaneously. Specifically, the graph learning subproblems are solved using the primal-dual splitting (PDS) algorithm, while the signal update has a closed-form solution. Parameters in this iterative algorithm are learned from training data by unrolling the iteration with deep algorithm unrolling. Experimental results on synthetic and real-world data demonstrate that the proposed method outperforms existing model- and deep learning-based graph signal denoising methods.

eess.SP↗