How can we accurately classify graphs using only positive and unlabeled instances? This setting commonly arises in real-world tasks. For example, in drug side effect prediction, each drug is represented as a graph based on its chemical structure, and only those observed to cause adverse effects are labeled as positive. The remaining drugs are left unlabeled—not because they are confirmed safe, but because such side effects have not yet been discovered or reported. A challenge is that positive and negative graphs often share similar substructures, making it difficult for models to capture the subtle structural differences that distinguish true positives among unlabeled ones. This difficulty is further exacerbated by the absence of explicit negative labels, which leaves the model without clear guidance on how to separate informative from non-informative patterns. We propose Delta-PU, an accurate method for PU graph classification. Delta-PU performs dual reweighting: hop-level reweighting to emphasize informative substructures during pooling, and graph-level reweighting to suppress ambiguous unlabeled graphs. This dual mechanism allows the model to progressively focus on discriminative patterns while reducing the uncertainty introduced by unlabeled instances. Extensive experiments demonstrate that Delta-PU achieves the state-of-the-art performance in PU graph classification.

Many real-world datasets including stock prices or disease records are represented as regular or irregular tensors across multiple domains.How can we accurately capture patterns from both irregular and regular tensors in a newly emerging domain by leveraging existing ones from multiple domains?This problem is crucial for applications such as identifying patterns of new diseases using data from existing ones. A main challenge is that the new target tensors contain limited information due to their recent emergence. Previously, PARAFAC2- and PARAFAC-based methods have been widely used to find patterns in irregular and regular tensors, respectively, through decomposing them into latent factors. However, they cannot effectively transfer knowledge from previously known tensors to the new one. In this work, we propose a fast and accurate domain adaptation method for tensor decomposition. We proposeMeta-P2for irregular tensors andMeta-Pfor regular tensors. BothMeta-P2andMeta-Plearn general and easily-adaptable information– - referred to as the meta factor—from multiple source domains. Using this meta factor, they efficiently identify patterns in a new target tensor. Extensive experiments on real-world datasets show thatMeta-P2andMeta-Pachieve the state-of-the-art performance across various downstream tasks, including missing value prediction and anomaly detection.

Given an edge-incomplete graph, how can we accurately find its missing links? The problem aims to discover the missing relations between entities when their relationships are represented as a graph. Edge-incomplete graphs are prevalent in real-world due to practical limitations, such as not checking all users when adding friends in a social network. Addressing the problem is crucial for various tasks, including recommending friends in social networks and finding references in citation networks. However, previous approaches rely heavily on the given edge-incomplete (observed) graph, making it challenging to consider the missing (unobserved) links. In this paper, we propose PULL, an accurate link prediction method based on the positive-unlabeled (PU) learning. PULL treats the observed edges in the training graph as positive examples, and the unconnected node pairs as unlabeled ones. PULL effectively prevents the link predictor from blindly trusting the observed graph by proposing latent variables for every edge, and leveraging the expected graph structure with respect to these variables. Extensive experiments on real- world datasets show that PULL consistently outperforms the baselines for predicting links in edge-incomplete graphs.

How can we accurately predict the signs of unseen links in partially observed signed graphs? Signed graphs are widely used to represent complex relationships in areas such as social and biological networks. Although prior methods enhance representation learning by extending Graph Neural Networks with social theories, they rely on the unrealistic assumption that all link signs are known. In practice, however, link signs are often only partially labeled due to the high cost or difficulty of obtaining ground-truth annotations. For example, in the Bitcoin transaction network, only a subset of interactions can be labeled as trusted or untrusted, while many remain unlabeled. In this work, we propose PIGLET (PROBABILISTIC MESSAGE PASSING FOR SEMI-SUPERVISED LINK SIGN PREDICTION), a novel approach for accurate link sign prediction on signed graphs with partially observed sign labels. The main idea is to probabilistically interpret unlabeled links as both positive and negative based on a soft-labeling strategy, allowing information to be propagated through both types of edges. To mitigate the effect of uncertain predictions, we use confidence-based weights to downplay unreliable edges. PIGLET balances the importance of edges with relation-aware attention scores as well. PIGLET establishes a theoretical connection between the ExpectationMaximization (EM) algorithm and its iterative refinement of node embeddings and soft labels. Extensive experiments show that PIGLET consistently outperforms existing methods on realworld datasets under semi-supervised setting.

This study explores the role of mobility platforms in mitigating issues arising from information asymmetry about taxi services in South Korea. We employed conjoint analysis from a cognitive fit perspective and analyzed the marginal utilities of platform features using a mixed logit model. Our results show that platformization addresses negative experiences associated with information asymmetry and resolves long-standing problems associated with taxi services. Specifically, consumers prioritize information visualization and safety services, underscoring the platforms’ role in enhancing trust and safety as well as convenience. Despite the expansion into premium mobility experiences, the fundamental expectation from consumers remains access to reliable, safe services. This research contributes to understanding the impact of digital transformation on the mobility sector, emphasizing the need for strategic and policy interventions to leverage mobility platforms for improved service delivery.

Given an irregular tensor from a newly emerging domain, how can we quickly and accurately capture its patterns utilizing existing irregular tensors in multiple domains? The problem is of great importance for various tasks such as finding patterns of a new disease using pre-existing diseases data. This is challenging as new target tensors have limited information due to their recent emergence. Thus, carefully utilizing the existing source tensors for analyzing the target tensor is helpful. PARAFAC2 decomposition is a strong tool for finding the patterns of irregular tensors, and the patterns are used in many applications such as missing value prediction and anomaly detection. However, previous PARAFAC2-based works cannot adaptably handle newly emerging target tensors utilizing the source tensors.

Multimodal sentiment analysis has become an increasingly popular research area as the demand for multimodal online content is growing. For multimodal sentiment analysis, words can have different meanings depending on the linguistic context and non-verbal information, so it is crucial to understand the meaning of the words accordingly. In addition, the word meanings should be interpreted within the whole utterance context that includes nonverbal information. In this paper, we present a Context-driven Modality Shifting BERT with Contrastive Learning for linguistic, visual, acoustic Representations (CMSBERT-CLR), which incorporates the whole context's non-verbal and verbal information and aligns modalities more effectively through contrastive learning. First, we introduce a Context-driven Modality Shifting (CMS) to incorporate the non-verbal and verbal information within the whole context of the sentence utterance. Then, for improving the alignment of different modalities within a common embedding space, we apply contrastive learning. Furthermore, we use an exponential moving average parameter and label smoothing as optimization strategies, which can make the convergence of the network more stable and increase the flexibility of the alignment. In our experiments, we demonstrate that our approach achieves state-of-the-art results.

How can we classify graph-structured data only with positive labels? Graph-based positive-unlabeled (PU) learning is to train a binary classifier given only the positive labels when the relationship between examples is given as a graph. The problem is of great importance for various tasks such as detecting malicious accounts in a social network, which are difficult to be modeled by supervised learning when the true negative labels are absent. Previous works for graph-based PU learning assume that the prior distribution of positive nodes is known in advance, which is not true in many real-world cases. In this work, we propose GRAB (Graph-based Risk minimization with iterAtive Belief propagation), a novel end-to-end approach for graph-based PU learning that requires no class prior. GRAB models a given graph as a Markov network and runs the marginalization and update steps iteratively. The marginalization step estimates the marginals of latent variables, while the update step trains a classifier network utilizing the computed priors in the objective function. Extensive experiments on five datasets show that GRAB achieves state-of-the-art accuracy, even compared with previous methods that are given the true prior.

Today, many of the research innovations in software visualization and comprehension are evaluated on small-scale programs in a way that avoids actual human evaluation, despite the fact that these techniques are designed to help programmers develop and understand large and complex software. The investments required to perform such human studies often outweigh the need to publish. As such, the goal of this work (and toolkit) is to enable the evaluation of software visualizations of real-life software systems by its actual developers, as well as to understand the factors that influence adoption. The approach is to directly assist practicing software developers with visualizations through open and online collaboration tools. The mechanism by which we accomplish this goal is an online service that is linked through the projects' revision-control and build systems. We are calling this system SPIDER SENSE, and it includes web-based visualizations for software exploration that is supported by tools for mirroring development activities, automatic building and testing, and automatic instrumentation to gather dynamic-analysis data. In the future, we envision the system and toolkit to become a framework on which further visualizations and analyses are developed. SPIDER SENSE is open-source and publicly available for download and collaborative development.

The features of a mobile device already penetrate everyday life and support every moment in life. Mobile connection between people does not imply only communication way, rather it means a gateway to connect virtual world as well. In the present study, mobile device close a gadget recording everyday life named "Life diary". The life diary is embedded mobile phone application and automatically summarizes user's daily life and encourages looking back previous events. Life diary's value proposition exits in keeping memories and sharing them automatically among phone, pc, and web in a systematical way.