arXiv subjects

Junghoon Kim

Publications and source records attributed to Junghoon Kim.

At least 19 recordsLinked to original sources

arXiv2026

Efficient Computation of Maximum Flexi-Clique in Networks

Discovering large cohesive subgraphs is a key task for graph mining. Existing models, such as clique, k-plex, and {\gamma}-quasi-clique, use fixed density thresholds that overlook the natural decay of connectivity as the subgraph size increases. The Flexi-clique model overcomes this limitation by imposing a degree constraint that grows sub-linearly with subgraph size. We provide the algorithmic study of Flexi-clique, proving its NP-hardness and analysing its non-hereditary properties. To address its computational challenge, we propose the Flexi-Prune Algorithm FPA, a fast heuristic using core-based seeding and connectivity-aware pruning, and the Efficient Branch-and-Bound Algorithm EBA, an exact framework enhanced with multiple pruning rules. Experiments on large real-world and synthetic networks demonstrate that FPA achieves near-optimal quality at much lower cost, while EBA efficiently computes exact solutions. Flexi-clique thus provides a practical and scalable model for discovering large, meaningful subgraphs in complex networks.

cs.SI↗

arXiv2025

Puzzle: Scheduling Multiple Deep Learning Models on Mobile Device with Heterogeneous Processors

As deep learning models are increasingly deployed on mobile devices, modern mobile devices incorporate deep learning-specific accelerators to handle the growing computational demands, thus increasing their hardware heterogeneity. However, existing works on scheduling deep learning workloads across these processors have significant limitations: most studies focus on single-model scenarios rather than realistic multi-model scenarios, overlook performance variations from different hardware/software configurations, and struggle with accurate execution time estimation. To address these challenges, we propose a novel genetic algorithm-based methodology for scheduling multiple deep learning networks on heterogeneous processors by partitioning the networks into multiple subgraphs. Our approach incorporates three different types of chromosomes for partition/mapping/priority exploration, and leverages device-in-the-loop profiling and evaluation for accurate execution time estimation. Based on this methodology, our system, Puzzle, demonstrates superior performance in extensive evaluations with randomly generated scenarios involving nine state-of-the-art networks. The results demonstrate Puzzle can support 3.7 and 2.2 times higher request frequency on average compared to the two heuristic baselines, NPU Only and Best Mapping, respectively, while satisfying the equivalent level of real-time requirements.

cs.LG↗

arXiv2025

Experimental Analysis and Evaluation of Cohesive Subgraph Discovery

Retrieving cohesive subgraphs in networks is a fundamental problem in social network analysis and graph data management. These subgraphs can be used for marketing strategies or recommendation systems. Despite the introduction of numerous models over the years, a systematic comparison of their performance, especially across varied network configurations, remains unexplored. In this study, we evaluated various cohesive subgraph models using task-based evaluations and conducted extensive experimental studies on both synthetic and real-world networks. Thus, we unveil the characteristics of cohesive subgraph models, highlighting their efficiency and applicability. Our findings not only provide a detailed evaluation of current models but also lay the groundwork for future research by shedding light on the balance between the interpretability and cohesion of the subgraphs. This research guides the selection of suitable models for specific analytical needs and applications, providing valuable insights.

cs.SI↗

arXiv2025

Uncovering High-Order Cohesive Structures: Efficient (k,g)-Core Computation and Decomposition for Large Hypergraphs

Hypergraphs, increasingly utilised to model complex and diverse relationships in modern networks, have gained significant attention for representing intricate higher-order interactions. Among various challenges, cohesive subgraph discovery is one of the fundamental problems and offers deep insights into these structures, yet the task of selecting appropriate parameters is an open question. To address this question, we aim to design an efficient indexing structure to retrieve cohesive subgraphs in an online manner. The main idea is to enable the discovery of corresponding structures within a reasonable time without the need for exhaustive graph traversals. Our method enables faster and more effective retrieval of cohesive structures, which supports decision-making in applications that require online analysis of large-scale hypergraphs. Through extensive experiments on real-world networks, we demonstrate the superiority of our proposed indexing technique.

cs.SI↗

arXiv2025

Cohesive Subgraph Discovery in Hypergraphs: A Locality-Driven Indexing Framework

Hypergraphs, increasingly utilised for modelling complex and diverse relationships in modern networks, gain much attention representing intricate higher-order interactions. Among various challenges, cohesive subgraph discovery is one of the fundamental problems and offers deep insights into these structures, yet the task of selecting appropriate parameters is an open question. To handle that question, we aim to design an efficient indexing structure to retrieve cohesive subgraphs in an online manner. The main idea is to enable the discovery of corresponding structures within a reasonable time without the need for exhaustive graph traversals. This work can facilitate efficient and informed decision-making in diverse applications based on a comprehensive understanding of the entire network landscape. Through extensive experiments on real-world networks, we demonstrate the superiority of our proposed indexing technique.

cs.SI↗

arXiv2024

Revisiting Fake News Detection: Towards Temporality-aware Evaluation by Leveraging Engagement Earliness

Social graph-based fake news detection aims to identify news articles containing false information by utilizing social contexts, e.g., user information, tweets and comments. However, conventional methods are evaluated under less realistic scenarios, where the model has access to future knowledge on article-related and context-related data during training. In this work, we newly formalize a more realistic evaluation scheme that mimics real-world scenarios, where the data is temporality-aware and the detection model can only be trained on data collected up to a certain point in time. We show that the discriminative capabilities of conventional methods decrease sharply under this new setting, and further propose DAWN, a method more applicable to such scenarios. Our empirical findings indicate that later engagements (e.g., consuming or reposting news) contribute more to noisy edges that link real news-fake news pairs in the social graph. Motivated by this, we utilize feature representations of engagement earliness to guide an edge weight estimator to suppress the weights of such noisy edges, thereby enhancing the detection performance of DAWN. Through extensive experiments, we demonstrate that DAWN outperforms existing fake news detection methods under real-world environments. The source code is available at https://github.com/LeeJunmo/DAWN.

cs.SI↗

arXiv2024

Toward Reasoning on the Boundary: A Mixup-based Approach for Graph Anomaly Detection

While GNN-based detection methods excel at identifying overt outliers, they often struggle with boundary anomalies -- subtly camouflaged nodes that are difficult to distinguish from normal instances. This limitation highlights a fundamental gap in the reasoning capabilities of existing methods. We attribute this issue to the reliance of standard Graph Contrastive Learning (GCL) on easy negatives, which fosters the learning of simplistic decision boundaries. To address this issue, we propose ANOMIX, a framework that synthesizes informative hard negatives by linearly interpolating representations of normal and abnormal subgraphs. This graph mixup strategy intentionally populates the decision boundary with hard-to-detect samples. Through targeted experimental analysis, we demonstrate that ANOMIX successfully separates these boundary anomalies where state-of-the-art baselines fail, as shown by a clear distinction in the score distributions for these challenging cases. These findings suggest that synthesizing hard negatives via mixup is a potent strategy for refining GNN representation space, which in turn enhances its reasoning capacity for more robust and reliable graph anomaly detection. Code is available at https://github.com/missinghwan/ANOMIX.

cs.LG↗

arXiv2024

Beyond Trivial Edges: A Fractional Approach to Cohesive Subgraph Detection in Hypergraphs

Hypergraphs serve as a powerful tool for modeling complex relationships across domains like social networks, transactions, and recommendation systems. The (k,g)-core model effectively identifies cohesive subgraphs by assessing internal connections and co-occurrence patterns, but it is susceptible to inflated cohesiveness due to trivial hyperedges. To address this, we propose the $(k,g,p)$-core model, which incorporates the relative importance of hyperedges for more accurate subgraph detection. We develop both Na\"ive and Advanced pruning algorithms, demonstrating through extensive experiments that our approach reduces the execution frequency of costly operations by 51.9% on real-world datasets.

cs.SI↗

arXiv2024

Beam Training in mmWave Vehicular Systems: Machine Learning for Decoupling Beam Selection

Codebook-based beam selection is one approach for configuring millimeter wave communication links. The overhead required to reconfigure the transmit and receive beam pair, though, increases in highly dynamic vehicular communication systems. Location information coupled with machine learning (ML) beam recommendation is one way to reduce the overhead of beam pair selection. In this paper, we develop ML-based location-aided approaches to decouple the beam selection between the user equipment (UE) and the base station (BS). We quantify the performance gaps due to decoupling beam selection and also disaggregating the UE's location information from the BS. Our simulation results show that decoupling beam selection with available location information at the BS performs comparable to joint beam pair selection at the BS. Moreover, decoupled beam selection without location closely approaches the performance of beam pair selection at the BS when sufficient beam pairs are swept.

eess.SP↗

arXiv2023

Coding for Gaussian Two-Way Channels: Linear and Learning-Based Approaches

Although user cooperation cannot improve the capacity of Gaussian two-way channels (GTWCs) with independent noises, it can improve communication reliability. In this work, we aim to enhance and balance the communication reliability in GTWCs by minimizing the sum of error probabilities via joint design of encoders and decoders at the users. We first formulate general encoding/decoding functions, where the user cooperation is captured by the coupling of user encoding processes. The coupling effect renders the encoder/decoder design non-trivial, requiring effective decoding to capture this effect, as well as efficient power management at the encoders within power constraints. To address these challenges, we propose two different two-way coding strategies: linear coding and learning-based coding. For linear coding, we propose optimal linear decoding and discuss new insights on encoding regarding user cooperation to balance reliability. We then propose an efficient algorithm for joint encoder/decoder design. For learning-based coding, we introduce a novel recurrent neural network (RNN)-based coding architecture, where we propose interactive RNNs and a power control layer for encoding, and we incorporate bi-directional RNNs with an attention mechanism for decoding. Through simulations, we show that our two-way coding methodologies outperform conventional channel coding schemes (that do not utilize user cooperation) significantly in sum-error performance. We also demonstrate that our linear coding excels at high signal-to-noise ratios (SNRs), while our RNN-based coding performs best at low SNRs. We further investigate our two-way coding strategies in terms of power distribution, two-way coding benefit, different coding rates, and block-length gain.

cs.IT↗

arXiv2023

Rate-Splitting Multiple Access: The First Prototype and Experimental Validation of its Superiority over SDMA and NOMA

In multi-user multi-antenna communications, it is well-known in theory that Rate-Splitting Multiple Access (RSMA) can achieve a higher spectral efficiency than both Space Division Multiple Access (SDMA) and Non-Orthogonal Multiple Access (NOMA). However, an experimental evaluation of RSMA's performance, relative to SDMA and NOMA, is missing in the literature, which is essential to address the ongoing debate between RSMA and NOMA over which is better suited to handle most efficiently the available resources and interference in 6G. In this paper, we address this critical knowledge gap by realizing the first-ever RSMA prototype using software-defined radios. Through measurements using our prototype, we empirically solve the modulation and coding scheme limited sum throughput maximization problem for RSMA, SDMA and NOMA for the two-user multiple-input single-output (MISO) scenario over (a) different pairs of line-of-sight channels that vary in terms of their relative pathloss and spatial correlation, and with (b) different channel state information quality. We observe that RSMA achieves the highest sum throughput across all these cases, whereas SDMA and NOMA are effective only in some cases. Furthermore, RSMA also achieves better fairness at a higher sum throughput than both SDMA and NOMA.

eess.SP↗

arXiv2023

Exploring Cohesive Subgraphs in Hypergraphs: The (k,g)-core Approach

Identifying cohesive subgraphs in hypergraphs is a fundamental problem that has received recent attention in data mining and engineering fields. Existing approaches mainly focus on a strongly induced subhypergraph or edge cardinality, overlooking the importance of the frequency of co-occurrence. In this paper, we propose a new cohesive subgraph named (k,g)-core, which considers both neighbour and co-occurrence simultaneously. The $(k,g)$-core has various applications including recommendation system, network analysis, and fraud detection. To the best of our knowledge, this is the first work to combine these factors. We extend an existing efficient algorithm to find solutions for $(k,g)$-core. Finally, we conduct extensive experimental studies that demonstrate the efficiency and effectiveness of our proposed algorithm.

cs.SI↗

arXiv2023

Class Label-aware Graph Anomaly Detection

Unsupervised GAD methods assume the lack of anomaly labels, i.e., whether a node is anomalous or not. One common observation we made from previous unsupervised methods is that they not only assume the absence of such anomaly labels, but also the absence of class labels (the class a node belongs to used in a general node classification task). In this work, we study the utility of class labels for unsupervised GAD; in particular, how they enhance the detection of structural anomalies. To this end, we propose a Class Label-aware Graph Anomaly Detection framework (CLAD) that utilizes a limited amount of labeled nodes to enhance the performance of unsupervised GAD. Extensive experiments on ten datasets demonstrate the superior performance of CLAD in comparison to existing unsupervised GAD methods, even in the absence of ground-truth class label information. The source code for CLAD is available at \url{https://github.com/jhkim611/CLAD}.

cs.LG↗

arXiv2023

Label-based Graph Augmentation with Metapath for Graph Anomaly Detection

Graph anomaly detection has attracted considerable attention from various domain ranging from network security to finance in recent years. Due to the fact that labeling is very costly, existing methods are predominately developed in an unsupervised manner. However, the detected anomalies may be found out uninteresting instances due to the absence of prior knowledge regarding the anomalies looking for. This issue may be solved by using few labeled anomalies as prior knowledge. In real-world scenarios, we can easily obtain few labeled anomalies. Efficiently leveraging labelled anomalies as prior knowledge is crucial for graph anomaly detection; however, this process remains challenging due to the inherently limited number of anomalies available. To address the problem, we propose a novel approach that leverages metapath to embed actual connectivity patterns between anomalous and normal nodes. To further efficiently exploit context information from metapath-based anomaly subgraph, we present a new framework, Metapath-based Graph Anomaly Detection (MGAD), incorporating GCN layers in both the dual-encoders and decoders to efficiently propagate context information between abnormal and normal nodes. Specifically, MGAD employs GNN-based graph autoencoder as its backbone network. Moreover, dual encoders capture the complex interactions and metapath-based context information between labeled and unlabeled nodes both globally and locally. Through a comprehensive set of experiments conducted on seven real-world networks, this paper demonstrates the superiority of the MGAD method compared to state-of-the-art techniques. The code is available at https://github.com/missinghwan/MGAD.

cs.LG↗

arXiv2023

Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning

The design of codes for feedback-enabled communications has been a long-standing open problem. Recent research on non-linear, deep learning-based coding schemes have demonstrated significant improvements in communication reliability over linear codes, but are still vulnerable to the presence of forward and feedback noise over the channel. In this paper, we develop a new family of non-linear feedback codes that greatly enhance robustness to channel noise. Our autoencoder-based architecture is designed to learn codes based on consecutive blocks of bits, which obtains de-noising advantages over bit-by-bit processing to help overcome the physical separation between the encoder and decoder over a noisy channel. Moreover, we develop a power control layer at the encoder to explicitly incorporate hardware constraints into the learning optimization, and prove that the resulting average power constraint is satisfied asymptotically. Numerical experiments demonstrate that our scheme outperforms state-of-the-art feedback codes by wide margins over practical forward and feedback noise regimes, and provide information-theoretic insights on the behavior of our non-linear codes. Moreover, we observe that, in a long blocklength regime, canonical error correction codes are still preferable to feedback codes when the feedback noise becomes high.

cs.IT↗

arXiv2023

Learning-Based Adaptive User Selection in Millimeter Wave Hybrid Beamforming Systems

We consider a multi-user hybrid beamforming system, where the multiplexing gain is limited by the small number of RF chains employed at the base station (BS). To allow greater freedom for maximizing the multiplexing gain, it is better if the BS selects and serves some of the users at each scheduling instant, rather than serving all the users all the time. We adopt a two-timescale protocol that takes into account the mmWave characteristics, where at the long timescale an analog beam is chosen for each user, and at the short timescale users are selected for transmission based on the chosen analog beams. The goal of the user selection is to maximize the traditional Proportional Fair (PF) metric. However, this maximization is non-trivial due to interference between the analog beams for selected users. We first define a greedy algorithm and a "top-k" algorithm, and then propose a machine learning (ML)-based user selection algorithm to provide an efficient trade-off between the PF performance and the computation time. Throughout simulations, we analyze the performance of the ML-based algorithms under various metrics, and show that it gives an efficient trade-off in performance as compared to counterparts.

eess.SY↗

arXiv2022

Linear Coding for Gaussian Two-Way Channels

We consider linear coding for Gaussian two-way channels (GTWCs), in which each user generates the transmit symbols by linearly encoding both its message and the past received symbols (i.e., the feedback information) from the other user. In Gaussian one-way channels (GOWCs), Butman has proposed a well-developed model for linear encoding that encapsulates feedback information into transmit signals. However, such a model for GTWCs has not been well studied since the coupling of the encoding processes at the users in GTWCs renders the encoding design non-trivial and challenging. In this paper, we aim to fill this gap in the literature by extending the existing signal models in GOWCs to GTWCs. With our developed signal model for GTWCs, we formulate an optimization problem to jointly design the encoding/decoding schemes for both the users, aiming to minimize the weighted sum of their transmit powers under signal-to-noise ratio constraints. First, we derive an optimal form of the linear decoding schemes under any arbitrary encoding schemes employed at the users. Further, we provide new insights on the encoding design for GTWCs. In particular, we show that it is optimal that one of the users (i) does not transmit the feedback information to the other user at the last channel use, and (ii) transmits its message only over the last channel use. With these solution behaviors, we further simplify the problem and solve it via an iterative two-way optimization scheme. We numerically demonstrate that our proposed scheme for GTWCs achieves a better performance in terms of the transmit power compared to the existing counterparts, such as the non-feedback scheme and one-way optimization scheme.

cs.IT↗

arXiv2022

Acousto-optic volumetric gating for reflection-mode deep optical imaging within a scattering medium

The imaging depth of deep-tissue optical microscopy is governed by the performance of the gating operation that suppresses the multiply scattered waves obscuring the ballistic waves. Although various gating operations based on confocal, time-resolved/coherence-gated, and polarization-selective detections have proven to be effective, each has its own limitation; certain types of multiply scattered waves can bypass the gating. Here, we propose a method, volumetric gating, that introduces ultrasound focus to confocal reflectance imaging to suppress the multiply scattered waves traveling outside the ultrasonic focal volume. The volumetric gating axially rejects the multiply scattered wave traveling to a depth shallower than the object plane while suppressing the deeper penetrating portion that travels across the object plane outside the transversal extent of the ultrasonic focus of 30${\times}$90$ μm^2$. These joint gating actions along the axial and lateral directions attenuate the multiply scattered waves by a factor of 1/1000 or smaller, thereby extending the imaging depth to 12.1 times the scattering mean free path while maintaining the diffraction-limited resolution of 1.5 $μ$m. We demonstrated an increase in the imaging depth and contrast for internal tissue imaging of mouse colon and small intestine through their outer walls. We further developed theoretical and experimental frameworks to characterize the axial distribution of light trajectories inside scattering media. The volumetric gating will serve as an important addition to deep-tissue imaging modalities and a useful tool for studying wave propagation in scattering media.

physics.optics↗