This paper evaluates methods to categorize similar software packages in npm's network.
problem Finding similar packages in npm's large software dependency network.
method Using graph structure to categorize packages, focusing on npm's 216,911 packages.
result Developed methods for categorizing similar packages, useful for recommendation systems.
Generative Adversarial Network repairs software bugs without labeled data.
problem Automated repair of software vulnerabilities.
method Adversarial learning approach mapping between source and target domains.
result Effective at repairing software vulnerabilities, close to seq2seq approaches.
DRIFT uses RL to automate functional software testing efficiently.
problem Efficient and reliable automated software testing.
method DRIFT employs Q-learning with Graph Neural Networks on symbolic UI representations.
result DRIFT can robustly test software functionalities in a fully automated manner.
Paper proposes algorithms for embedding directed networks with text associated nodes.
problem Learning embeddings for directed networks with text associated nodes.
method PCTADW-1 and PCTADW-2 neural network algorithms.
result Embeddings improve node classification quality on software package dependency networks.
PyTorch Geometric Signed Directed fills the gap for GNNs on signed and directed graphs.
problem Lack of unified software packages for GNNs on signed and directed networks.
method Developed a software package with GNN models, synthetic and real-world data, and evaluation metrics.
result Demonstrates the effectiveness of the implemented methods through experiments.
This paper tackles co-design of neural hardware and software to improve efficiency.
problem Designing efficient deep learning systems that consider both hardware and software optimizations together.
method Developed a constrained Bayesian optimization framework to automatically identify profitable design points in the joint hardware/software design space.
result Improved energy-delay product by 18% (ResNet) and 40% (DQN) over hand-tuned systems.
Software tool enhances sampling efficiency in neural networks.
problem Efficiently sampling from posterior distributions in machine learning models.
method Ensemble quasi-Newton preconditioning method for Langevin dynamics.
result Significant improvement in sampling efficiency demonstrated.
FEDHC learns Bayesian networks efficiently for continuous data.
problem Efficiently learning Bayesian networks for continuous data.
method Forward Early Dropping Hill Climbing (FEDHC) algorithm.
result FEDHC is computationally efficient and produces accurate Bayesian networks.
Convolutional neural network summarizes code comments across multiple languages.
problem Insufficient or missing comments in source code.
method Language-agnostic encoder-decoder model with open vocabulary.
result Comparable results to state-of-the-art on single-language data; first results on multi-language data.
Improving software quality through effective organizational learning.
problem Lack of reliable quantification methods for software evolution.
method Leveraging application lifecycle management data to identify and address managerial practices.
result Effective learning from past processes improves software quality indirectly.
TreeCaps improves code comprehension for software developers.
problem Processing code efficiently for software developers.
method Tree-based capsule networks for capturing code syntactical structures and dependencies.
result TreeCaps outperforms other approaches in classifying program functionalities.
This paper explores RL for cyber defense in SDN, resisting poisoning attacks.
problem Adversaries exploit ML adaptability to poison training and evade classification.
method Investigates RL algorithms for autonomous cyber defense in SDN, studying various attack types.
result RL agents can effectively react to poisoning attacks in SDN.
Automatically explores geometric loci of curves using software networking.
problem Exploring hyperbolisms and geometric loci of plane curves.
method Parametric equations, Groebner bases, and elimination for deriving polynomial equations.
result Derives new constructions of lemniscates and other geometric loci.
Paper proposes a faster method for evaluating DNN hardware and software designs.
problem Reducing time for evaluating different DNN hardware and software designs.
method Using virtual hardware models to estimate DNN performance at the concept phase.
result Up to 92% accuracy in predicting DNN inference processing time.
funcGNN uses graph neural networks to estimate program similarity efficiently.
problem Estimating accurate program similarity for software engineering tasks.
method funcGNN trains on labeled CFG pairs to predict GED between unseen programs using effective embedding vectors.
result funcGNN achieves lower error rate (0.00194) and is 23 times faster than traditional methods.
Model predicts customer churn in financial institutions using neural networks.
problem Manual feature engineering in customer churn prediction.
method Developed a Multi-layer Perceptron model using Artificial Neural Network architecture.
result Artificial Neural Network model achieved comparable performance to Neuro Solution Infinity software.
TensorFuzz automates neural network debugging with fuzzing.
problem Debugging neural networks for rare inputs is challenging.
method Coverage-guided fuzzing with approximate nearest neighbor algorithms.
result TensorFuzz discovers numerical errors and undesirable behavior.
Paper presents machine learning approach for detecting software vulnerabilities.
problem Detect subtle security vulnerabilities in production software.
method Data-driven approach using machine learning on C and C++ code.
result Highest performing model achieves AUC of 0.87 on ROC curve.
DLL accelerates deep learning models up to 10x faster.
problem Improving deep learning training and inference speed.
method Novel software engineering strategies for accelerating DLL.
result DLL is up to 10x faster than other frameworks on CPU and GPU.
sparsebn learns large Bayesian networks from high-dimensional data.
problem Learning graphical models from large, high-dimensional datasets with interventions.
method Focuses on scalability and consistency in high-dimensional settings, learning causal networks from data.
result Achieves the goal of learning a causal network from data.
Multimodal deep learning improves flaw detection in software programs.
problem Current flaw detection relies on single software representations.
method Adapted multimodal deep learning models for flaw detection.
result Multimodal models outperform traditional deep learning models.
Paper introduces HISA for efficient FHE computations.
problem Efficiently evaluating encrypted neural networks.
method Developed HISA for FHE applications, including compiler and runtime.
result Generated code is faster than hand-optimized implementations.
Optical ESNs enable flexible, efficient machine learning with reduced energy.
problem Implementing universal computational capabilities in machine learning.
method Optical implementation of ESNs leveraging stimulated Brillouin scattering.
result Efficient, scalable, and memory-capable optical reservoir computing.
KnotPlot helps beginners and veterans use software for visualizing knots.
problem None explicitly stated in the abstract.
method Software introduction and background for users.
result Provides new and veteran users with KnotPlot functionality.
RNNs learn device models from input/output data.
problem Learning complex device models from limited data.
method Empirical study using RNNs to model six different devices.
result RNNs can generate functional software-only models of hardware devices.
Hierarchical spiking networks resist physical distortions for neuromorphic computing.
problem Distortions in physical neuromorphic implementations of spiking networks.
method Used hierarchical leaky integrate-and-fire neurons to create robust spiking networks.
result Hierarchical spiking networks are robust to physical distortions.
Deep model improves software code understanding.
problem Software code's long context challenges existing models.
method Inspired by human memory, uses LSTM for long-term dependencies.
result Demonstrated effectiveness on Java project corpus.
Firefly algorithm improves software effort estimation models.
problem Improving accuracy of software effort estimation models.
method Using Firefly Algorithm to optimize COCOMO-based models.
result High accuracy and significant error minimization of Firefly Algorithm.
Research proposes an ensemble learning model for efficient software defect prediction.
problem Efficient and cost-effective software testing to minimize project resources.
method Machine learning analysis on different datasets using KNN, Decision Tree, SVM, and Naïve Bayes.
result Ensemble learning model outperforms other techniques in accuracy, precision, recall, and F1-score.
OS-ELM outperforms other classifiers in software defect prediction.
problem Predicting software defects from imbalanced datasets.
method OS-ELM, oversampling with noise filtering, comparison with other classifiers.
result OS-ELM outperforms other classifiers in recall and balanced accuracy.
Survey of Graph Neural Networks for efficient computation.
problem Efficient processing of Graph Neural Networks (GNNs) is challenging.
method Review of GNN algorithms, software and hardware acceleration analysis.
result Distilled hardware-software, graph-aware, and communication-centric vision for GNN accelerators.
DeepSoft aims to model software development for risk prediction and intervention.
problem Manual feature engineering and traditional classification problems in software analytics.
method End-to-end deep learning framework using Long Short Term Memory architecture.
result DeepSoft predicts future risks and recommends interventions in software development.
EgoCoder synthesizes programs from text using neural networks.
problem Automatically generating programs to meet software developer demand.
method Hierarchical sequential neural network model to parse and synthesize programs.
result EgoCoder effectively captures hierarchical and sequential program patterns.
Deep learning improves gamma-ray energy estimation and event selection.
problem Improving gamma-ray event selection and energy estimation.
method Adapted convolutional neural networks (CNN) for gamma-ray astronomy.
result Significant improvement in gamma-ray energy estimation and event selection.
Improved software flaw detection using NAS on multimodal DL models.
problem Software flaw detection in multimodal deep learning models.
method Adapted NAS framework for multimodal learning, combined with multimodal deep learning models.
result Improved performance on the Juliet Test Suite.
Graph2Diff neural network predicts precise code changes for build errors.
problem Fixing build errors in software development.
method Represented code and errors as graphs, used Graph Neural Network to predict precise diffs.
result Graph2Diff achieves over double the accuracy of DeepDelta in predicting precise code changes.
Method predicts hardware resource usage by control software with guaranteed linear convergence.
problem Predicting time-varying hardware resource availability in control software.
method Path structured multimarginal Schrödinger bridge (MSBP) for learning stochastic resource usage.
result Guaranteed linear convergence to accurate prediction of hardware resource utilization.
Explores security challenges of machine learning in real-world systems.
problem Vulnerabilities in machine learning models deployed in safety-critical systems.
method Broadens systems security view of ML vulnerabilities, identifies novel challenges, proposes mitigation suggestions.
result Highlights novel challenges and proposes mitigation strategies for securing ML systems.
Two clustering algorithms optimize edge controller placement in wireless networks.
problem Optimizing edge controller placement in wireless edge networks.
method Deterministic annealing based clustering algorithms ECP-LL and ECP-LB.
result The algorithms achieve better balance between synchronization and delay costs.
Machine learning enhances fuzzing for better software testing.
problem Challenges in traditional fuzzing.
method Applications of machine learning to improve fuzzing.
result Machine learning tools have successfully addressed fuzzing bottlenecks.
Neural network identifies undeclared variables and infers their types.
problem Undeclared variable errors in programs.
method Trained on structural semantic details of AST, identifies and infers types of undeclared variables.
result Correctly identified and inferred types for 80% of programs with undeclared variable errors.
Develops neural networks for reductive Lie groups, enhancing symmetry respect.
problem Symmetry respect in neural networks for reductive Lie groups.
method General equivariant neural network architecture for any reductive Lie Group G.
result Demonstrates generality and performance in top quark decay tagging and shape recognition.
Accelerates data loading in deep neural network training by 30x.
problem Data loading is a bottleneck in deep neural network training.
method Locality-aware data loading method using software caches.
result More than 30x speedup in data loading.
Survey of software developers' experience with Github Copilot tool.
problem Investigate developers' acceptance of AI-generated code.
method Survey with 18 questions distributed to 42 programmers.
result Mixed developer opinions, mostly positive but reluctance to use.
Stochastic DNNs with memristive synapses perform well despite limited device variability.
problem Performance of DNNs with memristive synapses under limited dynamic range and variability.
method Stochastic training of DNNs with memristive synapses, focusing on variability optimization.
result Stochastic memristive DNNs suffer less than 3% loss in accuracy compared to floating point software baseline.
ReQuEST platform aims to simplify ML system evaluation across diverse hardware and software.
problem Complexity and time-consuming evaluation of machine learning systems across frameworks and hardware.
method Open co-design tournament platform with online public scoreboard, leveraging Collective Knowledge and ACM artifact methodology.
result Validation and sharing of reproducible machine learning system implementations.
Optuna introduces a new hyperparameter optimization framework.
problem Efficient hyperparameter optimization for machine learning models.
method Define-by-run API, efficient implementation, versatile architecture.
result Optuna is the first software meeting next-generation hyperparameter optimization criteria.
CLN improves collective classification accuracy using deep learning.
problem Collective classification in multi-relational domains is computationally challenging.
method Column Network (CLN) model for collective classification in multi-relational domains.
result CLN achieves higher accuracy than state-of-the-art rivals in various applications.