29 accepted papers
Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on
We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world applications often demand more than high-fidelity generation, requiring…
Lower limb exoskeletons assist users by supporting joint movements. Since joint motion patterns vary depending on how the user moves, accurately recognizing the type of movement (locomotion mode) is crucial for controlling the exoskeleton and ensuring user safety. Inspired by how humans use multiple…
Graph collaborative filtering (GCF) is a dominant paradigm in recommender systems, where contrastive learning (CL) objectives such as the Sampled Softmax (SSM) loss are widely used for optimization. However, it remains unclear how CL interacts with the prediction mechanism of GCF. By unfolding the p…
Achieving both speed and accuracy is a central challenge for real-world robot manipulation. While recent imitation learning approaches, including vision-language-action (VLA) models, have achieved remarkable precision and generalization, their execution speed is often limited by slow demonstration v…
Evaluating dataset quality is an essential task, as the performance of artificial intelligence (AI) systems heavily depends on it. A traditional method for evaluating dataset quality involves training an AI model on the dataset and testing it on a separate test set. However, this approach requires s…
The performance of a deep learning model on a specific task and dataset depends heavily on its neural architecture, motivating considerable efforts to rapidly and accurately identify architectures suited to the target task and dataset. To achieve this, researchers use machine learning models—typical…
Lower limb exoskeletons assist users by supporting joint movements. Since joint motion patterns vary depending on how the user moves, accurately recognizing the type of movement (locomotion mode) is crucial for controlling the exoskeleton and ensuring user safety. Inspired by how humans use multiple
Recent advances have demonstrated the effectiveness of graph-based machine learning on relational databases (RDBs) for predictive tasks. Such approaches require transforming RDBs into graphs, a process we refer to as RDB-to-graph modeling, where rows of tables are represented as nodes and foreign-k…
Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate guidance approaches fail to optimize target rewards effectively.…
While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In this work, we propose Graph Lingual Network (GLN), a GNN built on large language models (LLMs), with hidden representatio
The objective for establishing dense correspondence between paired images con- sists of two terms: a data term and a prior term. While conventional techniques focused on defining hand-designed prior terms, which are difficult to formulate, re- cent approaches have focused on learning the data term w…
How would randomly shuffling feature vectors among nodes from the same class affect graph neural networks (GNNs)? The feature shuffle, intuitively, perturbs the dependence between graph topology and features (A-X dependence) for GNNs to learn from. Surprisingly, we observe a consistent and significa…
The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no one-size-fits-all solution. Thus considerable efforts have been made to quickly and accurately estimate the performances of neural architectures without full training or evaluation f…
In this paper, we derive the Cramér-Rao bounds (CRBs) on the positioning errors for narrow-band low earth orbit positioning, navigation, and timing (LEO-PNT) systems. Fisher information analysis is performed to characterize the CRBs for errors in Doppler and carrier phase measurements. In addition,…
Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple nodes with hyperedges, and better capturing the topology is essential for effective representation learning. Recent advances in generative self-supervised learning (SSL) suggest that hypergraph neural net…
Radio simultaneous localization and mapping (SLAM) with active sensing, such as radar and LiDAR, faces difficulty in detecting mirror-like walls that cause specular reflection. To solve this problem, the proposed radio SLAM algorithm merges active and passive sensing. Passive sensing exploits low-fr…
Graph autoencoders (Graph-AEs) learn representations of given graphs by aiming to accurately reconstruct them. A notable application of Graph-AEs is graph-level anomaly detection (GLAD), whose objective is to identify graphs with anomalous topological structures and/or node features compared to the…
Graph Neural Networks (GNNs) have gained significant attention as a powerful modeling and inference method, especially for homophilic graph-structured data. To empower GNNs in heterophilic graphs, where adjacent nodes exhibit dissimilar labels or features, Signed Message Passing (SMP) has been widel…
Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability to handle multiple attributes per image. Recent truly-unsupervised methods adopt clustering approaches to easily provide per-sample on…
Image-text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image/text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model’s decision qual…
In this paper, we present a blockwise optimization method for masking-based networks (BLOOM-Net) for training scalable speech enhancement networks. Here, we design our network with a residual learning scheme and train the internal separator blocks sequentially to obtain a scalable masking-based deep…
Recent techniques to solve photorealistic style transfer within deep convolutional neural networks (CNNs) generally require intensive training from large-scale datasets, thus having limited applicability and poor generalization ability to unseen images or styles. To overcome this, we propose a novel…
This paper proposes a two-stage beam training and a channel estimation based on fast alternating least squares (FALS) for reconfigurable intelligent surface (RIS)-aided millimeter-wave systems. To reduce the beam training overhead, only selected columns and rows of the channel matrix are observed by…
A motion-based control interface promises flexible robot operations in dangerous environments by combining user intuitions with the robot's motor capabilities. However, designing a motion interface for non-humanoid robots, such as quadrupeds or hexapods, is not straightforward because different dyna…
Speech enhancement tasks have seen significant improvements with the advance of deep learning technology, but with the cost of increased computational complexity. In this study, we propose an adaptive boosting approach to learning locality sensitive hash codes, which represent audio spectra efficien…
In this paper, we propose a deep neural network based matrix completion approach for Internet of Things (IoT) localization. In the proposed method, we recast Euclidean distance matrix completion problem into the alternating minimization problem. By using a cascade of multiple deep neural networks to…
In 5G mmWave, simultaneous localization and mapping (SLAM) allows devices to exploit map information to improve their position estimate. Even the most basic SLAM filter based on a Rao-Blackwellized particle filter (RBPF) combined with a probability hypothesis density (PHD) map representation exhibit…
This paper proposes a Bitwise Gated Recurrent Unit (BGRU) network for the single-channel source separation task. Recurrent Neural Networks (RNN) require several sets of weights within its cells, which significantly increases the computational cost compared to the fully-connected networks. To mitigat…