This article examines a collection of assumptions used in the current literature on node anomaly detection in a network. The examination raises the question: What are anomalies in a network? Our attempt to answer this question has provided some interesting findings and led to some open questions. This is the first article which formally defines anomalies in a network and introduces the concept of self-verifiability of a detector without ground-truths in a network. They enable existing detectors to be categorized into two types along the line whether they are self-verifiable or not. We suggest a method to evaluate self-verifiable detectors without ground-truths as an alternative to the existing evaluation method that relies on ground-truths.

Cheng Qian, Bingxiang He, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Deep image prior (DIP) has shown great promise in tackling a variety of image restoration (IR) and general visual inverse problems, needing no training data. However, the resulting optimization process is often very slow, inevitably hindering DIP's practical usage for time-sensitive scenarios. In this paper, we focus on IR, and propose two crucial modifications to DIP that help achieve substantial speedup: 1) optimizing the DIP seed while freezing randomly-initialized network weights, and 2) reducing the network depth. In addition, we reintroduce explicit priors, such as sparse gradient prior-encoded by total-variation regularization, to preserve the DIP peak performance. We evaluate the proposed method on three IR tasks, including image denoising, image super-resolution, and image inpainting, against the original DIP and variants, as well as the competing metaDIP that uses meta-learning to learn good initializers with extra data. Our method is a clear winner in obtaining competitive restoration quality in a minimal amount of time. Our code is available at https://github.com/sun-umn/Deep-Random-Projector.

Deep image prior (DIP) has shown great promise in tackling a range of image restoration problems. However, its optimization is extremely sluggish, which inevitability hinders its practical usage when there are hard time constraints. To mitigate this issue, we propose a more compact and efficient model, dubbed random projector (RP), and freeze the convolutional layers of the neural network to prevent slow learning. We further make use of an explicit prior—total variation— to regularize the reconstructed natural images and promote pleasure-looking images. We evaluate our proposed method on different image restoration tasks such as image denoising and image inpainting, and conduct comparisons with DIP and its prevalent variants. The experimental results suggest that our proposed random projector achieves competitive restoration quality in terms of PSNR while it significantly reduces the optimization (OPT) time.

Graph anomaly detection has attracted a lot of interest recently. Despite their successes, existing detectors have at least two of the three weaknesses: (a) high computational cost which limits them to small-scale networks only; (b) existing treatment of subgraphs produces suboptimal detection accuracy; and (c) unable to provide an explanation as to why a node is anomalous, once it is identified. We identify that the root cause of these weaknesses is a lack of a proper treatment for subgraphs. A treatment called Subgraph Centralization for graph anomaly detection is proposed to address all the above weaknesses. Its importance is shown in two ways. First, we present a simple yet effective new framework called Graph-Centric Anomaly Detection (GCAD). The key advantages of GCAD over existing detectors including deep-learning detectors are: (i) better anomaly detection accuracy; (ii) linear time complexity with respect to the number of nodes; and (iii) it is a generic framework that admits an existing point anomaly detector to be used to detect node anomalies in a network. Second, we show that Subgraph Centralization can be incorporated into two existing detectors to overcome the above-mentioned weaknesses.

MOTIVATION: Enhancer-promoter interactions (EPIs) in the genome play an important role in transcriptional regulation. EPIs can be useful in boosting statistical power and enhancing mechanistic interpretation for disease- or trait-associated genetic variants in genome-wide association studies. Instead of expensive and time-consuming biological experiments, computational prediction of EPIs with DNA sequence and other genomic data is a fast and viable alternative. In particular, deep learning and other machine learning methods have been demonstrated with promising performance. RESULTS: First, using a published human cell line dataset, we demonstrate that a simple convolutional neural network (CNN) performs as well as, if no better than, a more complicated and state-of-the-art architecture, a hybrid of a CNN and a recurrent neural network. More importantly, in spite of the well-known cell line-specific EPIs (and corresponding gene expression), in contrast to the standard practice of training and predicting for each cell line separately, we propose two transfer learning approaches to training a model using all cell lines to various extents, leading to substantially improved predictive performance. AVAILABILITY AND IMPLEMENTATION: Computer code is available at https://github.com/zzUMN/Combine-CNN-Enhancer-and-Promoters. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Proof-carrying code (PCC) is a technique that allows code consumers to check whether the code is safe to execute or not through a formal safety proof provided by the code producer. And a certifying compiler makes PCC practical by compiling annotated source code into low-level code and proofs. In this paper we present a certifying compiler for a subset of the C programming language, named Clike, with built-in automated theorem provers. Clike programs can be compiled by ANSI C compiler without any modification. Our compiler is intended to deal with data structures such as singly-linked lists, doubly-linked lists and trees. At the source level, we have designed a program logic combining a constrained first-order logic and a fragment of separation logic. We use a verification-condition-based method, and the generated verification conditions are sent to the built-in automated theorem prover. Our prover will generate proof terms when the input formula is valid. The low-level verification framework follows Hoare-style verification methods. The assembly code, its specification and proofs are generated automatically based on a variant of Stack-based Certifying Assembly Programming (SCAP). We implement our certifying compiler prototype in SML/NJ and build our prover libraries using the meta logic provided by Coq. We have used our prototype to successfully certify a considerable number of programs manipulating linked-lists and binary trees.