arXiv subjects

Jongwoo Kim

Publications and source records attributed to Jongwoo Kim.

9 recordsLinked to original sources

arXiv2026

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face a fundamental limitation: they require separate training for each new graph, preventing universal generalization across diverse graph datasets. A critical challenge facing GNNs lies in their reliance on labeled training data for each individual graph, a requirement that hinders the capacity for universal node classification due to the heterogeneity inherent in graphs -- differences in homophily levels, community structures, and feature distributions across datasets. Inspired by the success of large language models (LLMs) that achieve in-context learning through massive-scale pre-training on diverse datasets, we introduce NodePFN. This universal node classification method generalizes to arbitrary graphs without graph-specific training. NodePFN learns posterior predictive distributions (PPDs) by training only on thousands of synthetic graphs generated from carefully designed priors. Our synthetic graph generation covers real-world graphs through the use of random networks with controllable homophily levels and structural causal models for complex feature-label relationships. We develop a dual-branch architecture combining context-query attention mechanisms with local message passing to enable graph-aware in-context learning. Extensive evaluation on 23 benchmarks demonstrates that a single pre-trained NodePFN achieves 71.27 average accuracy. These results validate that universal graph learning patterns can be effectively learned from synthetic priors, establishing a new paradigm for generalization in node classification.

cs.LG↗

arXiv2026

Leveraging Spatial Context for Positive Pair Sampling in Histopathology Image Representation Learning

Deep learning has shown strong potential in cancer classification from whole-slide images (WSIs), but the need for extensive expert annotations often limits its success. Annotation-free approaches, such as multiple instance learning (MIL) and self-supervised learning (SSL), have emerged as promising alternatives to traditional annotation-based methods. However, conventional SSL methods typically rely on synthetic data augmentations, which may fail to capture the spatial structure critical to histopathology. In this work, we propose a spatial context-driven positive pair sampling strategy that enhances SSL by leveraging the morphological coherence of spatially adjacent patches within WSIs. Our method is modular and compatible with established joint embedding SSL frameworks, including Barlow Twins, BYOL, VICReg, and DINOv2. We evaluate its effectiveness on both slide-level classification using MIL and patch-level linear probing. Experiments across four datasets demonstrate consistent performance improvements, with accuracy gains of 5\% to 10\% compared to standard augmentation-based sampling. These findings highlight the value of spatial context in improving representation learning for computational pathology and provide a biologically meaningful enhancement for pretraining models in annotation-limited settings. The code is available at https://anonymous.4open.science/r/contextual-pairs-E72F/.

cs.CV↗

arXiv2026

Aspect-Aware MOOC Recommendation in a Heterogeneous Network

MOOC recommendation systems have received increasing attention to help learners navigate and select preferred learning content. Traditional methods such as collaborative filtering and content-based filtering suffer from data sparsity and over-specialization. To alleviate these limitations, graph-based approaches have been proposed; however, they still rely heavily on manually predefined metapaths, which often capture only superficial structural relationships and impose substantial burdens on domain experts as well as significant engineering costs. To overcome these limitations, we propose AMR (Aspect-aware MOOC Recommendation), a novel framework that models path-specific multiple aspects by embedding the semantic content of nodes within each metapath. AMR automatically discovers metapaths through bi-directional walks, derives aspect-aware path representations using a bi-LSTM-based encoder, and incorporates these representations as edge features in the learner-learner and KC-KC subgraphs to achieve fine-grained semantically informed KC recommendations. Extensive experiments on the large-scale MOOCCube and PEEK datasets show that AMR consistently outperforms state-of-the-art graph neural network baselines across key metrics such as HR@K and nDCG@K. Further analysis confirms that AMR effectively captures rich path-specific aspect information, allowing more accurate recommendations than those methods that rely solely on predefined metapaths. The code will be available upon accepted.

cs.AI↗

arXiv2026

FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedback

Going beyond the prediction of numerical scores, recent research in automated essay scoring has increasingly emphasized the generation of high-quality feedback that provides justification and actionable guidance. To mitigate the high cost of expert annotation, prior work has commonly relied on LLM-generated feedback to train essay assessment models. However, such feedback is often incorporated without explicit quality validation, resulting in the propagation of noise in downstream applications. To address this limitation, we propose FeedEval, an LLM-based framework for evaluating LLM-generated essay feedback along three pedagogically grounded dimensions: specificity, helpfulness, and validity. FeedEval employs dimension-specialized LLM evaluators trained on datasets curated in this study to assess multiple feedback candidates and select high-quality feedback for downstream use. Experiments on the ASAP++ benchmark show that FeedEval closely aligns with human expert judgments and that essay scoring models trained with FeedEval-filtered high-quality feedback achieve superior scoring performance. Furthermore, revision experiments using small LLMs show that the high-quality feedback identified by FeedEval leads to more effective essay revisions. We release our code and curated datasets at: https://github.com/BBeeChu/FeedEval.git.

cs.CL↗

arXiv2025

Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?

Foundation models pretrained on large data have demonstrated remarkable zero-shot generalization capabilities across domains. Building on the success of TabPFN for tabular data and its recent extension to time series, we investigate whether graph node classification can be effectively reformulated as a tabular learning problem. We introduce TabPFN-GN, which transforms graph data into tabular features by extracting node attributes, structural properties, positional encodings, and optionally smoothed neighborhood features. This enables TabPFN to perform direct node classification without any graph-specific training or language model dependencies. Our experiments on 12 benchmark datasets reveal that TabPFN-GN achieves competitive performance with GNNs on homophilous graphs and consistently outperforms them on heterophilous graphs. These results demonstrate that principled feature engineering can bridge the gap between tabular and graph domains, providing a practical alternative to task-specific GNN training and LLM-dependent graph foundation models.

cs.LG↗

arXiv2025

Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning

Recent advancements in graph neural networks (GNNs) and heterogeneous GNNs (HGNNs) have advanced node embeddings and relationship learning for various tasks. However, existing methods often rely on domain-specific predefined meta-paths, which are coarse-grained and focus solely on aspects like node type, limiting their ability to capture complex interactions. We introduce MF2Vec, a model that uses multi-faceted (fine-grained) paths instead of predefined meta-paths. MF2Vec extracts paths via random walks and generates multi-faceted vectors, ignoring predefined schemas. This method learns diverse aspects of nodes and their relationships, constructs a homogeneous network, and creates node embeddings for classification, link prediction, and clustering. Extensive experiments show that MF2Vec outperforms existing methods, offering a more flexible and comprehensive framework for analyzing complex networks. The code is available at https://anonymous.4open.science/r/MF2Vec-6ABC.

cs.LG↗

arXiv2025

MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Images

Cancer diagnosis has greatly benefited from the integration of whole-slide images (WSIs) with multiple instance learning (MIL), enabling high-resolution analysis of tissue morphology. Graph-based MIL (GNN-MIL) approaches have emerged as powerful solutions for capturing contextual information in WSIs, thereby improving diagnostic accuracy. However, WSIs require significant computational and infrastructural resources, limiting accessibility in resource-constrained settings. Conventional light microscopes offer a cost-effective alternative, but applying GNN-MIL to such data is challenging due to extensive redundant images and missing spatial coordinates, which hinder contextual learning. To address these issues, we introduce MicroMIL, the first weakly-supervised MIL framework specifically designed for images acquired from conventional light microscopes. MicroMIL leverages a representative image extractor (RIE) that employs deep cluster embedding (DCE) and hard Gumbel-Softmax to dynamically reduce redundancy and select representative images. These images serve as graph nodes, with edges computed via cosine similarity, eliminating the need for spatial coordinates while preserving contextual information. Extensive experiments on a real-world colon cancer dataset and the BreakHis dataset demonstrate that MicroMIL achieves state-of-the-art performance, improving both diagnostic accuracy and robustness to redundancy. The code is available at https://github.com/kimjongwoo-cell/MicroMIL

cs.CV↗

arXiv2022

Indefinite and Bidirectional Near Infrared Nanocrystal Photoswitching

Materials whose luminescence can be switched by optical stimulation drive technologies ranging from superresolution imaging1-4, nanophotonics5, and optical data storage6-8, to targeted pharmacology, optogenetics, and chemical reactivity9. These photoswitchable probes, including organic fluorophores and proteins, are prone to photodegradation, and often require phototoxic doses of ultraviolet (UV) or visible light. Colloidal inorganic nanoparticles have significant stability advantages over existing photoswitchable materials, but the ability to switch emission bidirectionally, particularly with NIR light, has not been reported with nanoparticles. Here, we present 2-way, near-infrared (NIR) photoswitching of avalanching nanoparticles (ANPs), showing full optical control of upconverted emission using phototriggers in the NIR-I and NIR-II spectral regions useful for subsurface imaging. Employing single-step photodarkening10-13 and photobrightening12,14-18, we demonstrate indefinite photoswitching of individual nanoparticles (>1000 cycles over 7 h) in ambient or aqueous conditions without measurable photodegradation. Critical steps of the photoswitching mechanism are elucidated by modeling and by measuring the photon avalanche properties of single ANPs in both bright and dark states. Unlimited, reversible photoswitching of ANPs enables indefinitely rewritable 2D and 3D multi-level optical patterning of ANPs, as well as optical nanoscopy with sub-Å localization superresolution that allows us to distinguish individual ANPs within tightly packed clusters.

physics.optics↗

arXiv2020

Direct Measurement of Curvature-Dependent Surface Tension in a Capillary-Condensed Alcohol Nanomeniscus

Surface tension is a key parameter for understanding nucleation from the very initial stage of phase transformation. Although surface tension has been predicted to vary with the curvature of the liquid-vapor interface, particularly at the large curvature of, e.g., the subnanometric critical nucleus, experimental study still remains challenging due to inaccessibility to such a small cluster. Here, by directly measuring the critical size of a single capillary-condensed nanomeniscus using atomic force microscopy, we address the curvature dependence of surface tension of alcohols and observe the surface tension is doubled for ethanol and n-propanol with the radius-of-curvature of ~ -0.46 nm. We also find that the interface of larger negative (positive) curvature exhibits the larger (smaller) surface tension, which evidently governs nucleation at ~ 1 nm scale, indicating more facilitated nucleation than normally expected. Such well characterized curvature effects contribute to better understanding and accurate analysis of nucleation occurring in various fields including material science and atmospheric science.

cond-mat.mes-hall↗