More Like this

1. Using stochastic block models for community detection

   https://doi.org/10.1007/s41109-025-00747-2  

   Vu-Le, The-Anh; Park, Minhyuk; Chen, Ian; Warnow, Tandy (December 2026, Applied Network Science)

   Abstract A recent study reported by Park et al. (Improved community detection using stochastic block models, Springer, Heidelberg, 2025) in Complex Networks and their Applications 2024 showed that clusterings from three Stochastic Block Models (SBMs) in graph-tool, a popular software package, often had internally disconnected clusters when used on large real-world or synthetic networks. To address this issue, Park et al. (Improved community detection using stochastic block models, Springer, Heidelberg, 2025) presented a simple technique, Well-Connected Clusters (WCC), that repeatedly finds and removes small edge cuts of size at most$$\log _{10}n$$in clusters, wherenis the number of nodes in the cluster, and showed that treatment of graph-tool SBM clusterings with WCC improves accuracy. Here we examine the question of cluster connectivity for clusterings computed using other SBM software or nested SBMs within graph-tool. Our study, using a wide range of real-world and synthetic networks ranging up to more than a million nodes, shows that all tested SBM clustering methods frequently produce communities that are disconnected, and that graph-tool improves on PySBM. We provide insight into why graph-tool degree-corrected SBM clustering produces disconnected clusters by examining the description length formula it uses, and explore the impact of modifications to the description length formula. Finally, we show that WCC generally provides an improvement in accuracy for both flat and nested SBMs, except for cases where nearly all nodes in the network are in very sparse ground-truth clusters. We also demonstrate that WCC scales to networks with millions of nodes. 

   more » « less
2. EC-SBM synthetic network generator

   https://doi.org/10.1007/s41109-025-00701-2  

   Vu-Le, The-Anh; Anne, Lahari; Chacko, George; Warnow, Tandy (December 2025, Applied Network Science)

   Abstract Generating high-quality synthetic networks with realistic community structure is vital to effectively evaluate community detection algorithms. In this study, we propose a new synthetic network generator called the Edge-Connected Stochastic Block Model (EC-SBM). The goal of EC-SBM is to take a given clustered real-world network and produce a synthetic network that resembles the clustered real-world network with respect to both network and community-specific criteria. In particular, we focus on simulating the internal edge connectivity of the clusters in the reference clustered network. Our performance study on large real-world networks shows that EC-SBM is generally more accurate with respect to network and community criteria than currently used approaches for this problem. Furthermore, we demonstrate that EC-SBM can complete analyses on several real-world networks with millions of nodes. 

   more » « less
3. Learning Two-Layer Neural Networks with Symmetric Inputs

   Ge, Rong; Kuditipudi, Rohith; Li, Zhize; Wang, Xiang (July 2019, International Conference on Learning Representations)

   We give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network y = Aσ(Wx) + ξ, where A,W are weight matrices, ξ represents noise, and the number of neurons in the hidden layer is no larger than the input or output, our algorithm is guaranteed to recover the parameters A,W of the ground-truth network. The only requirement on the input x is that it is symmetric, which still allows highly complicated and structured input. Our algorithm is based on the method-of-moments framework and extends several results in tensor decompositions. We use spectral algorithms to avoid the complicated non-convex optimization in learning neural networks. Experiments show that our algorithm can robustly learn the ground-truth neural network with a small number of samples for many symmetric input distributions. 

   more » « less
4. OpenWaters: Photorealistic Simulations For Underwater Computer Vision

   https://doi.org/10.1145/3491315.3491336  

   Mousavi, Mehdi; Vaidya, Shardul; Sutradhar, Razat; Ashok, Ashwin (November 2021, The 15th International Conference on Underwater Networks & Systems)

   In this paper, we present OpenWaters, a real-time open-source underwater simulation kit for generating photorealistic underwater scenes. OpenWaters supports creation of massive amount of underwater images by emulating diverse real-world conditions. It allows for fine controls over every variable in a simulation instance, including geometry, rendering parameters like ray-traced water caustics, scattering, and ground-truth labels. Using underwater depth (distance between camera and object) estimation as the use-case, we showcase and validate the capabilities of OpenWaters to model underwater scenes that are used to train a deep neural network for depth estimation. Our experimental evaluation demonstrates depth estimation using synthetic underwater images with high accuracy, and feasibility of transfer-learning of features from synthetic to real-world images. 

   more » « less
5. Benefits of Synthetically Pre-trained Depth-Prediction Networks for Indoor/Outdoor Image Classification

   https://doi.org/10.1109/WACVW58289.2023.00040  

   Lin, Kelly X.; Cho, Irene; Walimbe, Amey; Zamora, Bryan A.; Rich, Alex; Zhang, Sirius Z.; Höllerer, Tobias (January 2023, 2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW))

   Ground truth depth information is necessary for many computer vision tasks. Collecting this information is chal-lenging, especially for outdoor scenes. In this work, we propose utilizing single-view depth prediction neural networks pre-trained on synthetic scenes to generate relative depth, which we call pseudo-depth. This approach is a less expen-sive option as the pre-trained neural network obtains ac-curate depth information from synthetic scenes, which does not require any expensive sensor equipment and takes less time. We measure the usefulness of pseudo-depth from pre-trained neural networks by training indoor/outdoor binary classifiers with and without it. We also compare the difference in accuracy between using pseudo-depth and ground truth depth. We experimentally show that adding pseudo-depth to training achieves a 4.4% performance boost over the non-depth baseline model on DIODE, a large stan-dard test dataset, retaining 63.8% of the performance boost achieved from training a classifier on RGB and ground truth depth. It also boosts performance by 1.3% on another dataset, SUN397, for which ground truth depth is not avail-able. Our result shows that it is possible to take information obtained from a model pre-trained on synthetic scenes and successfully apply it beyond the synthetic domain to real-world data. 

   more » « less