论文检索

Yuchen Yan, Peiyan Zhang, Zheng Fang 0007, Qingqing Long

The "Graph pre-training and fine-tuning" paradigm has significantly improved Graph Neural Networks(GNNs) by capturing general knowledge without manual annotations for downstream tasks. However, due to the immense gap of data and tasks between the pre-training and fine-tuning stages, the model performance is still limited. Inspired by prompt fine-tuning in Natural Language Processing(NLP), many endeavors have been made to bridge the gap in graph domain. But existing methods simply reformulate the form of fine-tuning tasks to the pre-training ones. With the premise that the pre-training graphs are compatible with the fine-tuning ones, these methods typically operate in transductive setting. In order to generalize graph pre-training to inductive scenario where the fine-tuning graphs might significantly differ from pre-training ones, we propose a novel graph prompt based method called Inductive Graph Alignment Prompt(IGAP). Firstly, we unify the mainstream graph pre-training frameworks and analyze the essence of graph pre-training from graph spectral theory. Then we identify the two sources of the data gap in inductive setting: (i) graph signal gap and (ii) graph structure gap. Based on the insight of graph pre-training, we propose to bridge the graph signal gap and the graph structure gap with learnable prompts in the spectral space. A theoretical analysis ensures the effectiveness of our method. At last, we conduct extensive experiments among nodes classification and graph classification tasks under the transductive, semi-inductive and inductive settings. The results demonstrate that our proposed method can successfully bridge the data gap under different settings.

Peiyan Zhang, Chaozhuo Li, Liying Kang, Feiran Huang, Senzhang Wang, Xing Xie 0001, Sunghun Kim 0001

We investigate node representation learning on text-attributed graphs (TAGs), where nodes are associated with text information. Although recent studies on graph neural networks (GNNs) and pretrained language models (PLMs) have exhibited their power in encoding network and text signals, respectively, less attention has been paid to delicately coupling these two types of models on TAGs. Specifically, existing GNNs rarely model text in each node in a contextualized way; existing PLMs can hardly be applied to characterize graph structures due to their sequence architecture. To address these challenges, we propose HASH-CODE, a High-frequency Aware Spectral Hierarchical Contrastive Selective Coding method that integrates GNNs and PLMs into a unified model. Different from previous "cascaded architectures" that directly add GNN layers upon a PLM, our HASH-CODE relies on five self-supervised optimization objectives to facilitate thorough mutual enhancement between network and text signals in diverse granularities. Moreover, we show that existing contrastive objective learns the low-frequency component of the augmentation graph and propose a high-frequency component (HFC)-aware contrastive learning objective that makes the learned embeddings more distinctive. Extensive experiments on six real-world benchmarks substantiate the efficacy of our proposed approach. In addition, theoretical analysis and item embedding visualization provide insights into our model interoperability.

Mingguo He, Zhewei Wei, Shikun Feng, Zhengjie Huang, Weibin Li 0004, Yu Sun 0029, Dianhai Yu

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-based methods to aggregate information, i.e., manually selected meta-paths or some heuristic modules, lacking theoretical guarantees. Furthermore, these methods cannot learn arbitrary valid heterogeneous graph filters within the spectral domain, which have limited expressiveness. To tackle these issues, we present a positive spectral heterogeneous graph convolution via positive noncommutative polynomials. Then, using this convolution, we propose PSHGCN, a novel Positive Spectral Heterogeneous Graph Convolutional Network. PSHGCN offers a simple yet effective method for learning valid heterogeneous graph filters. Moreover, we demonstrate the rationale of PSHGCN in the graph optimization framework. We conducted an extensive experimental study to show that PSHGCN can learn diverse heterogeneous graph filters and outperform all baselines on open benchmarks. Notably, PSHGCN exhibits remarkable scalability, efficiently handling large real-world graphs comprising millions of nodes and edges. Our codes are available at https://github.com/ivam-he/PSHGCN.

Siddhant Saxena, Shounak Ghatak, Raghu Kolla, Debashis Mukherjee, Tanmoy Chakraborty 0002

Message passing on hypergraphs has been a standard framework for learning higher-order correlations between hypernodes. Recently-proposed hypergraph neural networks (HGNNs) can be categorized into spatial and spectral methods based on their design choices. In this work, we analyze the impact of change in hypergraph topology on the suboptimal performance of HGNNs and propose DPHGNN, a novel dual-perspective HGNN that introduces equivariant operator learning to capture lower-order semantics by inducing topology-aware spatial and spectral inductive biases. DPHGNN employs a unified framework to dynamically fuse lower-order explicit feature representations from the underlying graph into the super-imposed hypergraph structure. We benchmark DPHGNN over eight benchmark hypergraph datasets for the semi-supervised hypernode classification task and obtain superior performance compared to seven state-of-the-art baselines. We also provide a theoretical framework and a synthetic hypergraph isomorphism test to express the power of spatial HGNNs and quantify the expressivity of DPHGNN beyond the Generalized Weisfeiler Leman (1-GWL) test. Finally, DPHGNN was deployed by our partner e-commerce company, Meesho for the Return-to-Origin (RTO) prediction task, which shows ~7% higher macro F1-Score than the best baseline.

Shaowen Peng, Xin Liu 0020, Kazunari Sugiyama, Tsunenori Mine

It has been shown that the effectiveness of graph convolutional network (GCN) for recommendation is attributed to the spectral graph filtering. Most GCN-based methods consist of a graph filter or followed by a low-rank mapping optimized based on supervised training. However, we show two limitations suppressing the power of graph filtering: (1) Lack of generality. Due to the varied noise distribution, graph filters fail to denoise sparse data where noise is scattered across all frequencies, while supervised training results in worse performance on dense data where noise is concentrated in middle frequencies that can be removed by graph filters without training. (2) Lack of expressive power. We theoretically show that linear GCN (LGCN) that is effective on collaborative filtering (CF) cannot generate arbitrary embeddings, implying the possibility that optimal data representation might be unreachable. To tackle the first limitation, we show close relation between noise distribution and the sharpness of spectrum where a sharper spectral distribution is more desirable causing data noise to be separable from important features without training. Based on this observation, we propose a generalized graph normalization (G2N) with hyperparameters adjusting the sharpness of spectral distribution in order to redistribute data noise to assure that it can be removed by graph filtering without training. As for the second limitation, we propose an individualized graph filter (IGF) adapting to the different confidence levels of the user preference that interactions can reflect, which is proved to be able to generate arbitrary embeddings. By simplifying LGCN, we further propose a simplified graph filtering for CF (SGFCF) which only requires the top-K singular values for recommendation. Finally, experimental results on four datasets with different density settings demonstrate the effectiveness and efficiency of our proposed methods.

Jiahong Ma, Mingguo He, Zhewei Wei

Spectral Graph Neural Networks have demonstrated superior performance in graph representation learning. However, many current methods focus on employing shared polynomial coefficients for all nodes, i.e., learning node-unified filters, which limits the filters' flexibility for node-level tasks. The recent DSF attempts to overcome this limitation by learning node-wise coefficients based on positional encoding. However, the initialization and updating process of the positional encoding are burdensome, hindering scalability on large-scale graphs. In this work, we propose a scalable node-wise filter, PolyAttn. Leveraging the attention mechanism, PolyAttn can directly learn node-wise filters in an efficient manner, offering powerful representation capabilities. Building on PolyAttn, we introduce the whole model, named PolyFormer. In the lens of Graph Transformer models, PolyFormer, which calculates attention scores within nodes, shows great scalability. Moreover, the model captures spectral information, enhancing expressiveness while maintaining efficiency. With these advantages, PolyFormer offers a desirable balance between scalability and expressiveness for node-level tasks. Extensive experiments demonstrate that our proposed methods excel at learning arbitrary node-wise filters, showing superior performance on both homophilic and heterophilic graphs, and handling graphs containing up to 100 million nodes. The code is available at https://github.com/air029/PolyFormer.

Renqiang Luo, Huafei Huang 0001, Shuo Yu 0001, Zhuoyang Han, Estrid He, Xiuzhen Zhang 0001, Feng Xia 0001

Fairness-aware Graph Neural Networks (GNNs) often face a challenging trade-off, where prioritizing fairness may require compromising utility. In this work, we re-examine fairness through the lens of spectral graph theory, aiming to reconcile fairness and utility within the framework of spectral graph learning. We explore the correlation between sensitive features and spectrum in GNNs, using theoretical analysis to delineate the similarity between original sensitive features and those after convolution under different spectra. Our analysis reveals a reduction in the impact of similarity when the eigenvectors associated with the largest magnitude eigenvalue exhibit directional similarity. Based on these theoretical insights, we propose FUGNN, a novel spectral graph learning approach that harmonizes the conflict between fairness and utility. FUGNN ensures algorithmic fairness and utility by truncating the spectrum and optimizing eigenvector distribution during the encoding process. The fairness-aware eigenvector selection reduces the impact of convolution on sensitive features while concurrently minimizing the sacrifice of utility. FUGNN further optimizes the distribution of eigenvectors through a transformer architecture. By incorporating the optimized spectrum into the graph convolution network, FUGNN effectively learns node representations. Experiments on six real-world datasets demonstrate the superiority of FUGNN over baseline methods. The codes are available at https://github.com/yushuowiki/FUGNN.

Longlong Lin, Tao Jia 0001, Zeli Wang, Jin Zhao 0003, Rong-Hua Li 0001

Higher-order graph clustering aims to partition the graph using frequently occurring subgraphs (i.e., motifs), instead of the lower-order edges, as the atomic clustering unit, which has been recognized as the state-of-the-art solution in ground truth community detection and knowledge discovery. Motif conductance is one of the most promising higher-order graph clustering models due to its strong interpretability. However, existing motif conductance based graph clustering algorithms are mainly limited by a seminal two-stage reweighting computing framework, needing to enumerate all motif instances to obtain an edge-weighted graph for partitioning. However, such a framework has two-fold vital defects: (1) It can only provide a quadratic bound for the motif with three vertices, and whether there is provable clustering quality for other motifs is still an open question. (2) The enumeration procedure of motif instances incurs prohibitively high costs against large motifs or large dense graphs due to combinatorial explosions. Besides, expensive spectral clustering or local graph diffusion on the edge-weighted graph also makes existing methods unable to handle massive graphs with millions of nodes. To overcome these dilemmas, we propose a Provable and Scalable Motif Conductance algorithm PSMC, which has a fixed and motif-independent approximation ratio for any motif. Specifically, PSMC first defines a new vertex metric Motif Resident based on the given motif, which can be computed locally. Then, it iteratively deletes the vertex with the smallest motif resident value very efficiently using novel dynamic update technologies. Finally, it outputs the locally optimal result during the above iterative process. To further boost efficiency, we propose several effective bounds to estimate the motif resident value of each vertex, which can greatly reduce computational costs. Empirical results on real-life and synthetic demonstrate that our proposed algorithms achieve 3.2-32 times speedup and improve the quality by at least 12 times than the state-of-the art baselines.

Wenying Duan, Tianxiang Fang, Hong Rao, Xiaoxi He

In this paper, we present a novel method to significantly enhance the computational efficiency of Adaptive Spatial-Temporal Graph Neural Networks (ASTGNNs) by introducing the concept of the Graph Winning Ticket (GWT), derived from the Lottery Ticket Hypothesis (LTH). By adopting a pre-determined star topology as a GWT prior to training, we balance edge reduction with efficient information propagation, reducing computational demands while maintaining high model performance. Both the time and memory computational complexity of generating adaptive spatial-temporal graphs is significantly reduced from O(N2) to O(N). Our approach streamlines the ASTGNN deployment by eliminating the need for exhaustive training, pruning, and retraining cycles, and demonstrates empirically across various datasets that it is possible to achieve comparable performance to full models with substantially lower computational costs. Specifically, our approach enables training ASTGNNs on the largest scale spatial-temporal dataset using a single A6000 equipped with 48 GB of memory, overcoming the out-of-memory issue encountered during original training and even achieving state-of-the-art performance. Furthermore, we delve into the effectiveness of the GWT from the perspective of spectral graph theory, providing substantial theoretical support. This advancement not only proves the existence of efficient sub-networks within ASTGNNs but also broadens the applicability of the LTH in resource-constrained settings, marking a significant step forward in the field of graph neural networks. Code is available at https://anonymous.4open.science/r/paper-1430.

Yingpeng Du, Ziyan Wang, Zhu Sun 0001, Yining Ma 0001, Hongzhi Liu 0001, Jie Zhang 0002

Recently, much effort has been devoted to modeling users' multi-interests (aka multi-faceted preferences) based on their behaviors, aiming to accurately capture users' complex preferences. Existing methods attempt to model each interest of users through a distinct representation, but these multi-interest representations easily collapse into similar ones due to a lack of effective guidance. In this paper, we propose a generic multi-interest method for sequential recommendation, achieving disentangled representation learning of diverse interests technically and theoretically. To alleviate the collapse issue of multi-interests, we propose to conduct item partition guided by their likelihood of being co-purchased in a global view. It can encourage items in each group to focus on a discriminated interest, thus achieving effective disentangled learning of multi-interests. Specifically, we first prove the theoretical connection between item partition and spectral clustering, demonstrating its effectiveness in alleviating item-level and facet-level collapse issues that hinder existing disentangled methods. To efficiently optimize this problem, we then propose a Markov Random Field (MRF)-based method that samples small-scale sub-graphs from two separate MRFs, thus it can be approximated with a cross-entropy loss and optimized through contrastive learning. Finally, we perform multi-task learning to seamlessly align item partition learning with multi-interest modeling for more accurate recommendation. Experiments on three real-world datasets show that our method significantly outperforms state-of-the-art methods and can flexibly integrate with existing multi-interest models as a plugin to enhance their performances.

Lixian Zhang, Runmin Dong, Shuai Yuan, Jinxiao Zhang, Mengxuan Chen, Juepeng Zheng, Haohuan Fu

Nighttime light (NTL) remote sensing observation serves as a unique proxy for quantitatively assessing progress toward meeting a series of Sustainable Development Goals (SDGs), such as poverty estimation, urban sustainable development, and carbon emission. However, existing NTL observations often suffer from pervasive degradation and inconsistency, limiting their utility for computing the indicators defined by the SDGs. In this study, we propose a novel approach to reconstruct high-resolution NTL images using multimodal remote sensing data. To support this research endeavor, we introduce DeepLightMD, a comprehensive dataset comprising data from five heterogeneous sensors, offering fine spatial resolution and rich spectral information at a national scale. Additionally, we present DeepLightSR, a calibration-aware method for multi-modality super-resolution. DeepLightSR integrates calibration-aware alignment, an auxiliary-to-main multi-modality fusion, and an auxiliary-embedded refinement to effectively address spatial heterogeneity, fuse diversely representative features, and enhance performance in ×8 super-resolution tasks. Extensive experiments demonstrate the superiority of DeepLightSR over 8 competing methods, as evidenced by improvements in PSNR (2.01 dB ~ 13.25 dB) and PIQE (0.49 ~ 9.32). Our findings underscore the practical significance of our proposed dataset and model in reconstructing high-resolution NTL data, supporting efficiently and quantitatively assessing the SDG progress. The code and data will be available at https://github.com/xian1234/DeepLight.

Chengjie Zhou, Chao Che, Pengfei Wang, Qiang Zhang

Time series forecasting has essential applications across various domains. For instance, forecasting power time series can optimize energy usage and bolster grid stability and reliability. Existing models based on transformer architecture are limited to classical design, ignoring the impact of spatial information and noise on model architecture design. Therefore, we propose an atypical design of Transformer-based models for multivariate time series forecasting. This design consists of two critical components: (i) spectral clustering center of time series employed as the focal point for attention computation; (ii) alternating attention mechanism wherein each query transformer is compatible with spectral clustering centers, executing attention at the sequence level instead of the token level. The alternating design has a two-fold benefit: firstly, it eliminates the uncertainty noise present in the dependent variable sequence of the channel input, and secondly, it incorporates the Euclidean distance to mitigate the impact of extreme values on the attention matrix, thereby aligning predictions more closely to the sequence's natural progression. Experiments on ten real-world datasets, encompassing Wind, Electricity, Weather, and others, demonstrate that our Spectral Central Alternating Transformer (SCAT) outperforms state-of-the-art methods (SOTA) by an average of 42.8% in prediction performance in power time series forecasting.

Heng-Kai Zhang, Yi-Ge Zhang, Zhi Zhou, Yu-Feng Li

Graph-based consistency principle has been successfully applied to many semi-supervised problems in machine learning. Its performance largely depends on the quality of augmented graphs, which has been recently proven that revealing graph properties and maintaining the invariance of graphs are crucial for good performance. However, existing topology- or feature-based augmentation methods are spectrally non-localized -- important spectrums are disturbed throughout the entire frequency range, and their invariance may not be well preserved. Efforts on this issue remain to be limited. This paper proposes a simple yet effective model called Localized SPectral AugmentatioN (LSPAN), which perturbs a concentrated part of graph spectrum with equivalent intensity using Fourier orthogonality, so as to enhance graph spectrum preservation as well as model prediction. Moreover, it also avoids the significant training time of inverse Fourier transform. Extensive empirical evaluation on real-world datasets clearly shows the performance gain of spectrally localized augmentation, as well as its good convergence and efficiency compared to existing graph methods.

Qinke Ni, Hongyu Zhang, Cunhang Fan, Shengbing Pei, Chang Zhou, Zhao Lv

Auditory attention decoding (AAD) aims to recognize the attended speaker based on electroencephalography (EEG) signals in multi-talker environments. Most AAD methods only focus on the temporal or frequency domain, but neglect the relationships between these two domains, which results in the inability to simultaneously consider both time-varying and spectral-spatial information. To address this issue, this paper proposes a dual-branch parallel network with temporal-frequency fusion for AAD, named DBPNet, which consists of the temporal attentive branch and the frequency residual branch. Specifically, the temporal attentive branch aims to capture the time-varying features in the EEG time-series signal. The frequency residual branch aims to extract spectral-spatial features of multi-band EEG signals by the residual convolution. Finally, these dual branches are fused to consider both EEG signals time-varying and spectral-spatial features and get classification results. Experimental results show that compared with the best baseline, DBPNet achieves a relative improvement of 20.4% with a 0.1-second decision window for the MM-AAD dataset, but the number of trainable parameters is reduced by about 91 times.

Shunyang Zhang, Senzhang Wang, Hao Miao, Hao Chen, Changjun Fan, Jian Zhang

Multivariant time series (MTS) data are usually incomplete in real scenarios, and imputing the incomplete MTS is practically important to facilitate various time series mining tasks. Recently, diffusion model-based MTS imputation methods have achieved promising results by utilizing CNN or attention mechanisms for temporal features learning. However, it is hard to adaptively trade off the diverse effects of local and global temporal features by simply combining CNN and attention. To address this issue, we propose a Score-weighted Convolutional Diffusion Model (Score-CDM for short), whose backbone consists of a Score-weighted Convolution Module (SCM) and an Adaptive Reception Module (ARM). SCM adopts a score map to capture the global temporal features in the time domain, while ARM uses a Spectral2Time Window Block (S2TWB) to convolve the local time series data in the spectral domain. Benefiting from the time convolution properties of Fast Fourier Transformation, ARM can adaptively change the receptive field of the score map, and thus effectively balance the local and global temporal features. We conduct extensive evaluations on three real MTS datasets of different domains, and the result verifies the effectiveness of the proposed Score-CDM.

Yijun Bei, Xing Zhou, Erteng Liu, Yang Gao, Sen Lin, Kewei Gao, Zunlei Feng

The emergence of AIGC has brought attention to the issue of generating realistic deceptive content. While AIGC has the potential to revolutionize content creation, it also facilitates criminal activities. Specifically, the manipulation of speech has been exploited in tele-fraud and financial fraud schemes, posing a significant threat to societal security. Current deep learning-based methods for detecting forged speech extract mixed features from the original speech, which often contain redundant information. Moreover, these methods fail to consider the distinct characteristics of human voice-specific features and the diversity of background environmental sounds. This paper introduces a framework called Discriminative fEature dEcoupling enhanceMent (DEEM) for detecting speech forgery. Initially, the framework decouples the original speech into human voice features and background sound features. Subsequently, DEEM enhances voice-specific features through temporal dimension aggregation and improves continuity-related features in the background sound map via spectral-dimension aggregation. By employing the decoupling enhancement features, extensive experiments demonstrate that DEEM achieves an accuracy improvement of over 5% on FoR dataset compared to the state-of-the-art methods.

Wei Mao, Guihong Wan, Haim Schweitzer

Spectral clustering is a powerful clustering technique. It leverages the spectral properties of graphs to partition data points into meaningful clusters. The most common criterion for evaluating multi-way spectral clustering is NCut. Column Subset Selection is an important optimization technique in the domain of feature selection and dimension reduction which aims to identify a subset of columns of a given data matrix that can be used to approximate the entire matrix. We show that column subset selection can be used to compute spectral clustering and use this to obtain new graph clustering algorithms.

Arnab Sarker, Peter Fisher, Joseph Gaudio, Anuradha Annaswamy

Analysis and synthesis of safety-critical autonomous systems are carried out using models which are often dynamic. Two central features of these dynamic systems are parameters and unmodeled dynamics. Much of feedback control design is parametric in nature and as such, accurate and fast estimation of the parameters in the modeled part of the dynamic system is a crucial property for designing risk-aware autonomous systems. This paper addresses the use of a spectral lines-based approach for estimating parameters of the dynamic model of an autonomous system. Existing literature has treated all unmodeled components of the dynamic system as sub-Gaussian noise and proposed parameter estimation using Gaussian noise-based exogenous signals. In contrast, we allow the unmodeled part to have deterministic unmodeled dynamics, which are almost always present in physical systems, in addition to sub-Gaussian noise. In addition, we propose a deterministic construction of the exogenous signal in order to carry out parameter estimation. We introduce a new tool kit which employs the theory of spectral lines, retains the stochastic setting, and leads to non-asymptotic bounds on the parameter estimation error. Unlike the existing stochastic approach, these bounds are tunable through an optimal choice of the spectrum of the exogenous signal leading to accurate parameter estimation. We also show that this estimation is robust to unmodeled dynamics, a property that is not assured by the existing approach. Finally, we show that under ideal conditions with no deterministic unmodeled dynamics, the proposed approach can ensure a Õ(√t) Regret, matching existing literature. Experiments are provided to support all theoretical derivations, which show that the spectral lines-based approach outperforms the Gaussian noise-based method when unmodeled dynamics are present, in terms of both parameter estimation error and Regret obtained using the parameter estimates with a Linear Quadratic Regulator in feedback.

Jian Li, Yong Liu, Weiping Wang

Kernel methods are powerful tools to capture nonlinear patterns behind given data but often lead to poor performance on complicated tasks compared to convolutional neural networks. The reason is that kernel methods are still shallow and fully connected models, failing to reveal hierarchical features and local interdependencies. In this paper, to acquire hierarchical and local knowledge, we incorporate kernel methods with deep architectures and convolutional operators in a spectral kernel learning framework. Based on the inverse Fourier transform and Rademacher complexity theory, we provide the generalization error bounds for the proposed model and prove that under suitable initialization, deeper networks lead to tighter error bounds. Inspired by theoretical findings, we finally completed the convolutional spectral kernel network (CSKN) with two additional regularizers and an initialization strategy. Extensive ablation results validate the effectiveness of non-stationary spectral kernel, multiple layers, additional regularizers, and the convolutional filters, which coincide with our theoretical findings. We further devise a VGG-type 8-layers CSKN, and it outperforms the existing kernel-based networks and popular CNN models on the medium-sized image classification tasks.

Eunseon Seong, Harim Lee, Dong-Kyu Chae

With the widespread adoption of IoT, wearable devices, and sensors, time series data from human subjects are significantly increasing in the healthcare domain. Due to the laborious nature of manual annotation in time series data and the requirement for human experts, self-supervised learning methods are attempted to alleviate the limited label situations. While existing self-supervised methods have been successful to achieve comparable performance to the fully supervised methods, there are still some limitations that need to be addressed, considering the nature of time series data from human subjects: In real-world clinical settings, data labels (e.g., sleep stages) are usually annotated by subject-level, and there is a substantial variation in patterns between subjects. Thus, a model should be designed to deal with not only the label scarcity but also subject-wise nature of data to ensure high performance in real-world scenarios. To mitigate these issues, we propose a novel self-supervised learning framework for human subject time series data: Subject-Aware Time Series Clustering (SA-TSC). In the unsupervised representation learning phase, SA-TSC adopts a subject-wise learning strategy rather than instance-wise learning which randomly samples data instances from different subjects within the batch during training. Specifically, we generate subject-graphs with our graph construction method based on Gumbel-Softmax and perform graph spectral clustering on each subject-graph. In addition, we utilize graph neural networks to capture dependencies between channels and design our own graph learning module motivated from self-supervised loss. Experimental results show the outstanding performance of our SA-TSC with the limited & subject-wise label setting, leading to its high applicability to the healthcare industry. The code is available at: https://github.com/DILAB-HYU/SA-TSC