More Like this

1. Semeru: A Memory-Disaggregated Managed Runtime

   Chenxi Wang, Haoran Ma; Zhenyuan Ruan, MIT; Khanh Nguyen, Texas A&M; Michael D. Bond, Ohio State; Ravi Netravali, Miryung Kim (November 2020, 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020, Virtual Event, November 4-6, 2020)

   null (Ed.)

   Resource-disaggregated architectures have risen in popularity for large datacenters. However, prior disaggregation systems are designed for native applications; in addition, all of them require applications to possess excellent locality to be efficiently executed. In contrast, programs written in managed languages are subject to periodic garbage collection (GC), which is a typical graph workload with poor locality. Although most datacenter applications are written in managed languages, current systems are far from delivering acceptable performance for these applications. This paper presents Semeru, a distributed JVM that can dramatically improve the performance of managed cloud applications in a memory-disaggregated environment. Its design possesses three major innovations: (1) a universal Java heap, which provides a unified abstraction of virtual memory across CPU and memory servers and allows any legacy program to run without modifications; (2) a distributed GC, which offloads object tracing to memory servers so that tracing is performed closer to data; and (3) a swap system in the OS kernel that works with the runtime to swap page data efficiently. An evaluation of Semeru on a set of widely-deployed systems shows very promising results. 

   more » « less
2. OpenWGL: Open-World Graph Learning

   Wu, Man; Pan, Shirui; Zhu, Xingquan (January 2020, Proc. Of the 20th IEEE International Conference on Data Mining, November 17-20, 2020, Sorrento, Italy)

   null (Ed.)

   In traditional graph learning tasks, such as node classification, learning is carried out in a closed-world setting where the number of classes and their training samples are provided to help train models, and the learning goal is to correctly classify unlabeled nodes into classes already known. In reality, due to limited labeling capability and dynamic evolving of networks, some nodes in the networks may not belong to any existing/seen classes, and therefore cannot be correctly classified by closed-world learning algorithms. In this paper, we propose a new open-world graph learning paradigm, where the learning goal is to not only classify nodes belonging to seen classes into correct groups, but also classify nodes not belonging to existing classes to an unseen class. The essential challenge of the openworld graph learning is that (1) unseen class has no labeled samples, and may exist in an arbitrary form different from existing seen classes; and (2) both graph feature learning and prediction should differentiate whether a node may belong to an existing/seen class or an unseen class. To tackle the challenges, we propose an uncertain node representation learning approach, using constrained variational graph autoencoder networks, where the label loss and class uncertainty loss constraints are used to ensure that the node representation learning are sensitive to unseen class. As a result, node embedding features are denoted by distributions, instead of deterministic feature vectors. By using a sampling process to generate multiple versions of feature vectors, we are able to test the certainty of a node belonging to seen classes, and automatically determine a threshold to reject nodes not belonging to seen classes as unseen class nodes. Experiments on real-world networks demonstrate the algorithm performance, comparing to baselines. Case studies and ablation analysis also show the rationale of our design for open-world graph learning. 

   more » « less
3. Graph mixup with soft alignments

   Hongyi Ling, Zhimeng Jiang (July 2023, ICML2023)

   We study graph data augmentation by mixup, which has been used successfully on images. A key operation of mixup is to compute a convex combination of a pair of inputs. This operation is straightforward for grid-like data, such as images, but challenging for graph data. The key difficulty lies in the fact that different graphs typically have different numbers of nodes, and thus there lacks a node-level correspondence between graphs. In this work, we propose S-Mixup, a simple yet effective mixup method for graph classification by soft alignments. Specifically, given a pair of graphs, we explicitly obtain node-level correspondence via computing a soft assignment matrix to match the nodes between two graphs. Based on the soft assignments, we transform the adjacency and node feature matrices of one graph, so that the transformed graph is aligned with the other graph. In this way, any pair of graphs can be mixed directly to generate an augmented graph. We conduct systematic experiments to show that S-Mixup can improve the performance and generalization of graph neural networks (GNNs) on various graph classification tasks. In addition, we show that S-Mixup can increase the robustness of GNNs against noisy labels. Our code is publicly available as part of the DIG package (https://github.com/divelab/DIG). 

   more » « less
4. HeapHopper: Bringing Bounded Model Checking to Heap Implementation Security

   Eckert, M. (August 2018, Proceedings of the USENIX conference)

   Heap metadata attacks have become one of the primary ways in which attackers exploit memory corruption vulnerabilities. While heap implementation developers have introduced mitigations to prevent and detect corruption, it is still possible for attackers to work around them. In part, this is because these mitigations are created and evaluated without a principled foundation, resulting, in many cases, in complex, inefficient, and ineffective attempts at heap metadata defenses. In this paper, we present HEAPHOPPER, an automated approach, based on model checking and symbolic execution, to analyze the exploitability of heap implementations in the presence of memory corruption. Using HEAPHOPPER, we were able to perform a systematic analysis of different, widely used heap implementations, finding surprising weaknesses in them. Our results show, for instance, how a newly introduced caching mechanism in ptmalloc (the heap allocator implementation used by most of the Linux distributions) significantly weakens its security. Moreover, HEAPHOPPER guided us in implementing and evaluating improvements to the security of ptmalloc, replacing an ineffective recent attempt at the mitigation of a specific form of heap metadata corruption with an effective defense. 

   more » « less
5. Graph embedding on biomedical networks: methods, applications and evaluations

   https://doi.org/10.1093/bioinformatics/btz718  

   Yue, Xiang; Wang, Zhen; Huang, Jingong; Parthasarathy, Srinivasan; Moosavinasab, Soheil; Huang, Yungui; Lin, Simon M; Zhang, Wen; Zhang, Ping; Sun, Huan; et al (October 2019, Bioinformatics)

   Abstract Motivation Graph embedding learning that aims to automatically learn low-dimensional node representations, has drawn increasing attention in recent years. To date, most recent graph embedding methods are evaluated on social and information networks and are not comprehensively studied on biomedical networks under systematic experiments and analyses. On the other hand, for a variety of biomedical network analysis tasks, traditional techniques such as matrix factorization (which can be seen as a type of graph embedding methods) have shown promising results, and hence there is a need to systematically evaluate the more recent graph embedding methods (e.g. random walk-based and neural network-based) in terms of their usability and potential to further the state-of-the-art. Results We select 11 representative graph embedding methods and conduct a systematic comparison on 3 important biomedical link prediction tasks: drug-disease association (DDA) prediction, drug–drug interaction (DDI) prediction, protein–protein interaction (PPI) prediction; and 2 node classification tasks: medical term semantic type classification, protein function prediction. Our experimental results demonstrate that the recent graph embedding methods achieve promising results and deserve more attention in the future biomedical graph analysis. Compared with three state-of-the-art methods for DDAs, DDIs and protein function predictions, the recent graph embedding methods achieve competitive performance without using any biological features and the learned embeddings can be treated as complementary representations for the biological features. By summarizing the experimental results, we provide general guidelines for properly selecting graph embedding methods and setting their hyper-parameters for different biomedical tasks. Availability and implementation As part of our contributions in the paper, we develop an easy-to-use Python package with detailed instructions, BioNEV, available at: https://github.com/xiangyue9607/BioNEV, including all source code and datasets, to facilitate studying various graph embedding methods on biomedical tasks. Supplementary information Supplementary data are available at Bioinformatics online. 

   more » « less