Publications without Fulltext
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/3
Browse
104 results
Search Results
Publication Metadata only Snoopie: a multi-GPU communication profiler and visualizer(Assoc Computing Machinery, 2024) Department of Computer Engineering; Issa, Mohammad Kefah Taha; Sasongko, Muhammad Aditya; Turimbetov, İlyas; Baydamirli, Javid; Sağbili, Doğan; Erten, Didem Unat; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringWith data movement becoming one of the most expensive bottlenecks in computing, the need for profiling tools to analyze communication becomes crucial for effectively scaling multi-GPU applications. While existing profiling tools including first-party software by GPU vendors are robust and excel at capturing compute operations within a single GPU, support for monitoring GPU-GPU data transfers and calls issued by communication libraries is currently inadequate. To fill these gaps, we introduce Snoopie, an instrumentation-based multi-GPU communication profiling tool built on NVBit, capable of tracking peer-to-peer transfers and GPU-centric communication library calls. To increase programmer productivity, Snoopie can attribute data movement to the source code line and the data objects involved. It comes with multiple visualization modes at varying granularities, from a coarse view of the data movement in the system as a whole to specific instructions and addresses. Our case studies demonstrate Snoopie's effectiveness in monitoring data movement, locating performance bugs in applications, and understanding concrete data transfers abstracted beneath communication libraries. The tool is publicly available at https://github.com/ParCoreLab/snoopie.Publication Metadata only Learning markerless robot-depth camera calibration and end-effector pose estimation(Ml Research Press, 2023) Department of Computer Engineering; Sefercik, Buğra Can; Akgün, Barış; Department of Computer Engineering; Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); College of Engineering; Graduate School of Sciences and EngineeringTraditional approaches to extrinsic calibration use fiducial markers and learning-based approaches rely heavily on simulation data. In this work, we present a learning-based markerless extrinsic calibration system that uses a depth camera and does not rely on simulation data. We learn models for end-effector (EE) segmentation, single-frame rotation prediction and keypoint detection, from automatically generated real-world data. We use a transformation trick to get EE pose estimates from rotation predictions and a matching algorithm to get EE pose estimates from keypoint predictions. We further utilize the iterative closest point algorithm, multiple-frames, filtering and outlier detection to increase calibration robustness. Our evaluations with training data from multiple camera poses and test data from previously unseen poses give sub-centimeter and sub-deciradian average calibration and pose estimation errors. We also show that a carefully selected single training pose gives comparable results. © 2023 Proceedings of Machine Learning Research. All rights reserved.Publication Metadata only HyperE2VID: improving event-based video reconstruction via hypernetworks(IEEE-Inst Electrical Electronics Engineers Inc, 2024) Ercan, Burak; Eker, Onur; Sağlam, Canberk; Erdem, Erkut; Department of Computer Engineering; Erdem, Aykut; Department of Computer Engineering; Koç Üniversitesi İş Bankası Enfeksiyon Hastalıkları Uygulama ve Araştırma Merkezi (EHAM) / Koç University İşbank Center for Infectious Diseases (KU-IS CID); College of Engineering;Event-based cameras are becoming increasingly popular for their ability to capture high-speed motion with low latency and high dynamic range. However, generating videos from events remains challenging due to the highly sparse and varying nature of event data. To address this, in this study, we propose HyperE2VID, a dynamic neural network architecture for event-based video reconstruction. Our approach uses hypernetworks to generate per-pixel adaptive filters guided by a context fusion module that combines information from event voxel grids and previously reconstructed intensity images. We also employ a curriculum learning strategy to train the network more robustly. Our comprehensive experimental evaluations across various benchmark datasets reveal that HyperE2VID not only surpasses current state-of-the-art methods in terms of reconstruction quality but also achieves this with fewer parameters, reduced computational requirements, and accelerated inference times.Publication Metadata only AffectON: Incorporating affect into dialog generation(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Bucinca, Zana; Department of Computer Engineering; Yemez, Yücel; Erzin, Engin; Sezgin, Tevfik Metin; Department of Computer Engineering; Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); College of EngineeringDue to its expressivity, natural language is paramount for explicit and implicit affective state communication among humans. The same linguistic inquiry (e.g., How are you?) might induce responses with different affects depending on the affective state of the conversational partner(s) and the context of the conversation. Yet, most dialog systems do not consider affect as constitutive aspect of response generation. In this article, we introduce AffectON, an approach for generating affective responses during inference. For generating language in a targeted affect, our approach leverages a probabilistic language model and an affective space. AffectON is language model agnostic, since it can work with probabilities generated by any language model (e.g., sequence-to-sequence models, neural language models, n-grams). Hence, it can be employed for both affective dialog and affective language generation. We experimented with affective dialog generation and evaluated the generated text objectively and subjectively. For the subjective part of the evaluation, we designed a custom user interface for rating and provided recommendations for the design of such interfaces. The results, both subjective and objective demonstrate that our approach is successful in pulling the generated language toward the targeted affect, with little sacrifice in syntactic coherence.Publication Metadata only Lessons learned from a Citizen Science Project for Natural Language Processing(Association for Computational Linguistics (ACL), 2023) Klie, Jan-Christoph; Lee, Ji-Ung; Stowe, Kevin; Moosavi, Nafise Sadat; Bates, Luke; Petrak, Dominic; de Castilho, Richard Eckart; Gurevych, Iryna; Department of Computer Engineering; Şahin, Gözde Gül; Department of Computer Engineering; Koç Üniversitesi İş Bankası Yapay Zeka Uygulama ve Araştırma Merkezi (KUIS AI)/ Koç University İş Bank Artificial Intelligence Center (KUIS AI); College of EngineeringMany Natural Language Processing (NLP) systems use annotated corpora for training and evaluation. However, labeled data is often costly to obtain and scaling annotation projects is difficult, which is why annotation tasks are often outsourced to paid crowdworkers. Citizen Science is an alternative to crowdsourcing that is relatively unexplored in the context of NLP. To investigate whether and how well Citizen Science can be applied in this setting, we conduct an exploratory study into engaging different groups of volunteers in Citizen Science for NLP by re-annotating parts of a pre-existing crowdsourced dataset. Our results show that this can yield high-quality annotations and attract motivated volunteers, but also requires considering factors such as scalability, participation over time, and legal and ethical issues. We summarize lessons learned in the form of guidelines and provide our code and data to aid future work on Citizen Science. © 2023 Association for Computational Linguistics.Publication Metadata only Implications of node selection in decentralized federated learning(IEEE, 2023) Department of Computer Engineering; Lodhi, Ahnaf Hannan; Akgün, Barış; Özkasap, Öznur; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringDecentralized Federated Learning (DFL) offers a fully distributed alternative to Federated Learning (FL). However, the lack of global information in a highly heterogeneous environment negatively impacts its performance. Node selection in FL has been suggested to improve both communication efficiency and convergence rate. In order to assess its impact on DFL performance, this work evaluates node selection using performance metrics. It also proposes and evaluates a time-varying parameterized node selection method for DFL employing validation accuracy and its per-round change. The mentioned criteria are evaluated using both hard and stochastic/soft selection on sparse networks. The results indicate that the bias associated with node selection adversely impacts performance as training progresses. Furthermore, under extreme conditions, soft selection is observed to result in higher diversity for better generalization, while a completely random selection is shown to be preferable with very limited participation.Publication Metadata only Histopathological classification of colon tissue images with self-supervised models(IEEE, 2023) Department of Computer Engineering; Erden, Mehmet Bahadır; Cansız, Selahattin; Demir, Çiğdem Gündüz; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of EngineeringDeep learning techniques have demonstrated their ability to facilitate medical image diagnostics by offering more precise and accurate predictions. Convolutional neural network (CNN) architectures have been employed for a decade as the primary approach to enable automated diagnosis. On the other hand, recently proposed vision transformers (ViTs) based architectures have shown success in various computer vision tasks. However, their efficacy in medical image classification tasks remains largely unexplored due to their requirement for large datasets. Nevertheless, significant performance gains can be achieved by leveraging self-supervised learning techniques through pretraining. This paper analyzes performance of self-supervised pretrained networks in medical image classification tasks. Results on colon histopathology images revealed that CNN based architectures are more effective when trained from scratch, while pretrained models could achieve similar levels of performance with limited data.Publication Metadata only Detection and mitigation of targeted data poisoning attacks in federated learning(IEEE, 2022) Department of Computer Engineering; Erbil, Pınar; Gürsoy, Mehmet Emre; Department of Computer Engineering; College of EngineeringFederated learning (FL) has emerged as a promising paradigm for distributed training of machine learning models. In FL, several participants train a global model collaboratively by only sharing model parameter updates while keeping their training data local. However, FL was recently shown to be vulnerable to data poisoning attacks, in which malicious participants send parameter updates derived from poisoned training data. In this paper, we focus on defending against targeted data poisoning attacks, where the attacker's goal is to make the model misbehave for a small subset of classes while the rest of the model is relatively unaffected. To defend against such attacks, we first propose a method called MAPPS for separating malicious updates from benign ones. Using MAPPS, we propose three methods for attack detection: MAPPS + X-Means, MAPPS + VAT, and their Ensemble. Then, we propose an attack mitigation approach in which a "clean" model (i.e., a model that is not negatively impacted by an attack) can be trained despite the existence of a poisoning attempt. We empirically evaluate all of our methods using popular image classification datasets. Results show that we can achieve > 95% true positive rates while incurring only < 2% false positive rate. Furthermore, the clean models that are trained using our proposed methods have accuracy comparable to models trained in an attack-free scenario.Publication Metadata only Beta poisoning attacks against machine learning models: extensions, limitations and defenses(IEEE, 2022) Department of Computer Engineering; Kara, Atakan; Köprücü, Nursena; Gürsoy, Mehmet Emre; Department of Computer Engineering; College of EngineeringThe rise of machine learning (ML) has made ML models lucrative targets for adversarial attacks. One of these attacks is Beta Poisoning, which is a recently proposed training-time attack based on heuristic poisoning of the training dataset. While Beta Poisoning was shown to be effective against linear ML models, it was originally developed with a fixed Gaussian Kernel Density Estimator (KDE) for likelihood estimation, and its effectiveness against more advanced, non-linear ML models has not been explored. In this paper, we advance the state of the art in Beta Poisoning attacks by making three novel contributions. First, we extend the attack so that it can be executed with arbitrary KDEs and norm functions. We integrate Gaussian, Laplacian, Epanechnikov and Logistic KDEs with three norm functions, and show that the choice of KDE can significantly impact attack effectiveness, especially when attacking linear models. Second, we empirically show that Beta Poisoning attacks are ineffective against non-linear ML models (such as neural networks and multi-layer perceptrons), even with our extensions. Results imply that the effectiveness of the attack decreases as model non-linearity and complexity increase. Finally, our third contribution is the development of a discriminator-based defense against Beta Poisoning attacks. Results show that our defense strategy achieves 99% and 93% accuracy in identifying poisoning samples on MNIST and CIFAR-10 datasets, respectively.Publication Metadata only GECTurk: grammatical error correction and detection dataset for Turkish(Association for Computational Linguistics, 2023) Department of Computer Engineering; Kara, Atakan; Sofian, Farrin Marouf; Yong-Xern Bond, Andrew; Şahin, Gözde Gül; Department of Computer Engineering; College of Engineering; Graduate School of Sciences and EngineeringGrammatical Error Detection and Correction (GEC) tools have proven useful for native speakers and second language learners. Developing such tools requires a large amount of parallel, annotated data, which is unavailable for most languages. Synthetic data generation is a common practice to overcome the scarcity of such data. However, it is not straightforward for morphologically rich languages like Turkish due to complex writing rules that require phonological, morphological, and syntactic information. In this work, we present a flexible and extensible synthetic data generation pipeline for Turkish covering more than 20 expert-curated grammar and spelling rules (a.k.a., writing rules) implemented through complex transformation functions. Using this pipeline, we derive 130,000 high-quality parallel sentences from professionally edited articles. Additionally, we create a more realistic test set by manually annotating a set of movie reviews. We implement three baselines formulating the task as i) neural machine translation, ii) sequence tagging, and iii) prefix tuning with a pretrained decoder-only model, achieving strong results. Furthermore, we perform exhaustive experiments on out-of-domain datasets to gain insights on the transferability and robustness of the proposed approaches. Our results suggest that our corpus, GECTurk, is high-quality and allows knowledge transfer for the out-of-domain setting. To encourage further research on Turkish GEC, we release our datasets, baseline models, and the synthetic data generation pipeline at https://github.com/GGLAB-KU/gecturk.