Paper Group ANR 962
Heterogeneous Collaborative Filtering. Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing. Manifold Forests: Closing the Gap on Neural Networks. Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases. Deep Learning and Gaussian Process based Band Assignment in Dual Band Systems. One-Shot Template …
Heterogeneous Collaborative Filtering
| Title | Heterogeneous Collaborative Filtering |
| Authors | Yifang Liu, Zhentao Xu, Cong Hui, Yi Xuan, Jessie Chen, Yuanming Shan |
| Abstract | Recommendation system is important to a content sharing/creating social network. Collaborative filtering is a widely-adopted technology in conventional recommenders, which is based on similarity between positively engaged content items involving the same users. Conventional collaborative filtering (CCF) suffers from cold start problem and narrow content diversity. We propose a new recommendation approach, heterogeneous collaborative filtering (HCF) to tackle these challenges at the root, while keeping the strength of collaborative filtering. We present two implementation algorithms of HCF for content recommendation and content dissemination. Experiment results demonstrate that our approach improve the recommendation quality in a real world social network for content creating and sharing. |
| Tasks | |
| Published | 2019-08-31 |
| URL | https://arxiv.org/abs/1909.01727v1 |
| https://arxiv.org/pdf/1909.01727v1.pdf | |
| PWC | https://paperswithcode.com/paper/heterogeneous-collaborative-filtering |
| Repo | |
| Framework | |
Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
| Title | Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing |
| Authors | En Li, Liekang Zeng, Zhi Zhou, Xu Chen |
| Abstract | As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is challenging to run computation-intensive DNN-based tasks on mobile devices due to the limited computation resources. What’s worse, traditional cloud-assisted DNN inference is heavily hindered by the significant wide-area network latency, leading to poor real-time performance as well as low quality of user experience. To address these challenges, in this paper, we propose Edgent, a framework that leverages edge computing for DNN collaborative inference through device-edge synergy. Edgent exploits two design knobs: (1) DNN partitioning that adaptively partitions computation between device and edge for purpose of coordinating the powerful cloud resource and the proximal edge resource for real-time DNN inference; (2) DNN right-sizing that further reduces computing latency via early exiting inference at an appropriate intermediate DNN layer. In addition, considering the potential network fluctuation in real-world deployment, Edgentis properly design to specialize for both static and dynamic network environment. Specifically, in a static environment where the bandwidth changes slowly, Edgent derives the best configurations with the assist of regression-based prediction models, while in a dynamic environment where the bandwidth varies dramatically, Edgent generates the best execution plan through the online change point detection algorithm that maps the current bandwidth state to the optimal configuration. We implement Edgent prototype based on the Raspberry Pi and the desktop PC and the extensive experimental evaluations demonstrate Edgent’s effectiveness in enabling on-demand low-latency edge intelligence. |
| Tasks | Change Point Detection |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.05316v1 |
| https://arxiv.org/pdf/1910.05316v1.pdf | |
| PWC | https://paperswithcode.com/paper/edge-ai-on-demand-accelerating-deep-neural |
| Repo | |
| Framework | |
Manifold Forests: Closing the Gap on Neural Networks
| Title | Manifold Forests: Closing the Gap on Neural Networks |
| Authors | Ronan Perry, Tyler M. Tomita, Jesse Patsolic, Benjamin Falk, Joshua T. Vogelstein |
| Abstract | Decision forests (DF), in particular random forests and gradient boosting trees, have demonstrated state-of-the-art accuracy compared to other methods in many supervised learning scenarios. In particular, DFs dominate other methods in tabular data, that is, when the feature space is unstructured, so that the signal is invariant to permuting feature indices. However, in structured data lying on a manifold—such as images, text, and speech—neural nets (NN) tend to outperform DFs. We conjecture that at least part of the reason for this is that the input to NN is not simply the feature magnitudes, but also their indices (for example, the convolution operation uses “feature locality”). In contrast, na"ive DF implementations fail to explicitly consider feature indices. A recently proposed DF approach demonstrates that DFs, for each node, implicitly sample a random matrix from some specific distribution. Here, we build on that to show that one can choose distributions in a \emph{manifold aware fashion}. For example, for image classification, rather than randomly selecting pixels, one can randomly select contiguous patches. We demonstrate the empirical performance of data living on three different manifolds: images, time-series, and a torus. In all three cases, our Manifold Forest (\Mf) algorithm empirically dominates other state-of-the-art approaches that ignore feature space structure, achieving a lower classification error on all sample sizes. This dominance extends to the MNIST data set as well. Moreover, both training and test time is significantly faster for manifold forests as compared to deep nets. This approach, therefore, has promise to enable DFs and other machine learning methods to close the gap with deep nets on manifold-valued data. |
| Tasks | Image Classification, Time Series |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11799v1 |
| https://arxiv.org/pdf/1909.11799v1.pdf | |
| PWC | https://paperswithcode.com/paper/manifold-forests-closing-the-gap-on-neural |
| Repo | |
| Framework | |
Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases
| Title | Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases |
| Authors | Maximilian Idahl, Megha Khosla, Avishek Anand |
| Abstract | In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide to identify subspaces in node embeddings learned from an entity graph derived from Wikipedia. We propose a method that given a concept finds a linear transformation to a subspace where the structure of the concept is retained. Our initial experiments show that we obtain low error in finding fine-grained concepts. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.05030v1 |
| https://arxiv.org/pdf/1910.05030v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-interpretable-concept-spaces-in-node |
| Repo | |
| Framework | |
Deep Learning and Gaussian Process based Band Assignment in Dual Band Systems
| Title | Deep Learning and Gaussian Process based Band Assignment in Dual Band Systems |
| Authors | Daoud Burghal, Rui Wang, Andreas F. Molisch |
| Abstract | We consider the band assignment (BA) problem in dual-band systems, where the basestation (BS) chooses one of the two available frequency bands (centimeter-wave and millimeter-wave bands) to communicate with the user equipment (UE). While the millimeter-wave band might offer higher data rate, there is a significant probability of outage during which the communication should be carried on the (more reliable) centimeter-wave band. We consider two variations of the BA problem, one-shot and sequential BA. For the former the BS uses only the currently observed information to decide whether to switch to the other frequency band, for the sequential BA, the BS uses a window of previously observed information to predict the best band for a future time step. We provide two approaches to solve the BA problem, (i) a deep learning approach that is based on Long Short Term Memory and/or multi-layer Neural Networks, and (ii) a Gaussian Process based approach, which relies on the assumption that the channel states are jointly Gaussian. We compare the achieved performances to several benchmarks in two environments: (i) a stochastic environment, and (ii) microcellular outdoor channels obtained by ray-tracing. In general, the deep learning solution shows superior performance in both environments. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10890v1 |
| http://arxiv.org/pdf/1902.10890v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-and-gaussian-process-based-band |
| Repo | |
| Framework | |
One-Shot Template Matching for Automatic Document Data Capture
| Title | One-Shot Template Matching for Automatic Document Data Capture |
| Authors | Pranjal Dhakal, Manish Munikar, Bikram Dahal |
| Abstract | In this paper, we propose a novel one-shot template-matching algorithm to automatically capture data from business documents with an aim to minimize manual data entry. Given one annotated document, our algorithm can automatically extract similar data from other documents having the same format. Based on a set of engineered visual and textual features, our method is invariant to changes in position and value. Experiments on a dataset of 595 real invoices demonstrate 86.4% accuracy. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10037v1 |
| https://arxiv.org/pdf/1910.10037v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-shot-template-matching-for-automatic |
| Repo | |
| Framework | |
A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization
| Title | A Survey of Techniques All Classifiers Can Learn from Deep Networks: Models, Optimizations, and Regularization |
| Authors | Alireza Ghods, Diane J Cook |
| Abstract | Deep neural networks have introduced novel and useful tools to the machine learning community. Other types of classifiers can potentially make use of these tools as well to improve their performance and generality. This paper reviews the current state of the art for deep learning classifier technologies that are being used outside of deep neural networks. Non-network classifiers can employ many components found in deep neural network architectures. In this paper, we review the feature learning, optimization, and regularization methods that form a core of deep network technologies. We then survey non-neural network learning algorithms that make innovative use of these methods to improve classification. Because many opportunities and challenges still exist, we discuss directions that can be pursued to expand the area of deep learning for a variety of classification algorithms. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04791v2 |
| https://arxiv.org/pdf/1909.04791v2.pdf | |
| PWC | https://paperswithcode.com/paper/techniques-all-classifiers-can-learn-from |
| Repo | |
| Framework | |
GRAVITAS: A Model Checking Based Planning and Goal Reasoning Framework for Autonomous Systems
| Title | GRAVITAS: A Model Checking Based Planning and Goal Reasoning Framework for Autonomous Systems |
| Authors | Hadrien Bride, Jin Song Dong, Ryan Green, Zhe Hou, Brendan Mahony, Martin Oxenham |
| Abstract | While AI techniques have found many successful applications in autonomous systems, many of them permit behaviours that are difficult to interpret and may lead to uncertain results. We follow the “verification as planning” paradigm and propose to use model checking techniques to solve planning and goal reasoning problems for autonomous systems. We give a new formulation of Goal Task Network (GTN) that is tailored for our model checking based framework. We then provide a systematic method that models GTNs in the model checker Process Analysis Toolkit (PAT). We present our planning and goal reasoning system as a framework called Goal Reasoning And Verification for Independent Trusted Autonomous Systems (GRAVITAS) and discuss how it helps provide trustworthy plans in an uncertain environment. Finally, we demonstrate the proposed ideas in an experiment that simulates a survey mission performed by the REMUS-100 autonomous underwater vehicle. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01380v1 |
| https://arxiv.org/pdf/1910.01380v1.pdf | |
| PWC | https://paperswithcode.com/paper/gravitas-a-model-checking-based-planning-and |
| Repo | |
| Framework | |
Quantum Logic Gate Synthesis as a Markov Decision Process
| Title | Quantum Logic Gate Synthesis as a Markov Decision Process |
| Authors | M. Sohaib Alam |
| Abstract | Reinforcement learning has witnessed recent applications to a variety of tasks in quantum programming. The underlying assumption is that those tasks could be modeled as Markov Decision Processes (MDPs). Here, we investigate the feasibility of this assumption by exploring its consequences for two of the simplest tasks in quantum programming: state preparation and gate compilation. By forming discrete MDPs, focusing exclusively on the single-qubit case, we solve for the optimal policy exactly through policy iteration. We find optimal paths that correspond to the shortest possible sequence of gates to prepare a state, or compile a gate, up to some target accuracy. As an example, we find sequences of H and T gates with length as small as 11 producing ~99% fidelity for states of the form (HT)^{n} 0> with values as large as n=10^{10}. This work provides strong evidence that reinforcement learning can be used for optimal state preparation and gate compilation for larger qubit spaces. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12002v1 |
| https://arxiv.org/pdf/1912.12002v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-logic-gate-synthesis-as-a-markov |
| Repo | |
| Framework | |
There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
| Title | There is Limited Correlation between Coverage and Robustness for Deep Neural Networks |
| Authors | Yizhen Dong, Peixin Zhang, Jingyi Wang, Shuang Liu, Jun Sun, Jianye Hao, Xinyu Wang, Li Wang, Jin Song Dong, Dai Ting |
| Abstract | Deep neural networks (DNN) are increasingly applied in safety-critical systems, e.g., for face recognition, autonomous car control and malware detection. It is also shown that DNNs are subject to attacks such as adversarial perturbation and thus must be properly tested. Many coverage criteria for DNN since have been proposed, inspired by the success of code coverage criteria for software programs. The expectation is that if a DNN is a well tested (and retrained) according to such coverage criteria, it is more likely to be robust. In this work, we conduct an empirical study to evaluate the relationship between coverage, robustness and attack/defense metrics for DNN. Our study is the largest to date and systematically done based on 100 DNN models and 25 metrics. One of our findings is that there is limited correlation between coverage and robustness, i.e., improving coverage does not help improve the robustness. Our dataset and implementation have been made available to serve as a benchmark for future studies on testing DNN. |
| Tasks | Face Recognition, Malware Detection |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.05904v1 |
| https://arxiv.org/pdf/1911.05904v1.pdf | |
| PWC | https://paperswithcode.com/paper/there-is-limited-correlation-between-coverage |
| Repo | |
| Framework | |
Selection Heuristics on Semantic Genetic Programming for Classification Problems
| Title | Selection Heuristics on Semantic Genetic Programming for Classification Problems |
| Authors | Claudia N. Sánchez, Mario Graff |
| Abstract | In a steady-state evolution, tournament selection traditionally uses the fitness function to select the parents, and negative selection chooses an individual to be replaced with an offspring. This contribution focuses on analyzing the behavior, in terms of performance, of different heuristics when used instead of the fitness function in tournament selection. The heuristics analyzed are related to measuring the similarity of the individuals in the semantic space. In addition, the analysis includes random selection and traditional tournament selection. These selection functions were implemented on our Semantic Genetic Programming system, namely EvoDAG, which is inspired by the geometric genetic operators and tested on 30 classification problems with a variable number of samples, variables, and classes. The result indicated that the combination of accuracy and the random selection, in the negative tournament, produces the best combination, and the difference in performances between this combination and the tournament selection is statistically significant. Furthermore, we compare EvoDAG’s performance using the selection heuristics against 18 classifiers that included traditional approaches as well as auto-machine-learning techniques. The results indicate that our proposal is competitive with state-of-art classifiers. Finally, it is worth to mention that EvoDAG is available as open source software. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07066v2 |
| https://arxiv.org/pdf/1907.07066v2.pdf | |
| PWC | https://paperswithcode.com/paper/selection-heuristics-on-semantic-genetic |
| Repo | |
| Framework | |
The Naked Sun: Malicious Cooperation Between Benign-Looking Processes
| Title | The Naked Sun: Malicious Cooperation Between Benign-Looking Processes |
| Authors | Fabio De Gaspari, Dorjan Hitaj, Giulio Pagnotta, Lorenzo De Carli, Luigi V. Mancini |
| Abstract | Recent progress in machine learning has generated promising results in behavioral malware detection. Behavioral modeling identifies malicious processes via features derived by their runtime behavior. Behavioral features hold great promise as they are intrinsically related to the functioning of each malware, and are therefore considered difficult to evade. Indeed, while a significant amount of results exists on evasion of static malware features, evasion of dynamic features has seen limited work. This paper thoroughly examines the robustness of behavioral malware detectors to evasion, focusing particularly on anti-ransomware evasion. We choose ransomware as its behavior tends to differ significantly from that of benign processes, making it a low-hanging fruit for behavioral detection (and a difficult candidate for evasion). Our analysis identifies a set of novel attacks that distribute the overall malware workload across a small set of cooperating processes to avoid the generation of significant behavioral features. Our most effective attack decreases the accuracy of a state-of-the-art classifier from 98.6% to 0% using only 18 cooperating processes. Furthermore, we show our attacks to be effective against commercial ransomware detectors even in a black-box setting. |
| Tasks | Behavioral Malware Detection, Malware Detection |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02423v1 |
| https://arxiv.org/pdf/1911.02423v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-naked-sun-malicious-cooperation-between |
| Repo | |
| Framework | |
Fast and Deep Graph Neural Networks
| Title | Fast and Deep Graph Neural Networks |
| Authors | Claudio Gallicchio, Alessio Micheli |
| Abstract | We address the efficiency issue for the construction of a deep graph neural network (GNN). The approach exploits the idea of representing each input graph as a fixed point of a dynamical system (implemented through a recurrent neural network), and leverages a deep architectural organization of the recurrent units. Efficiency is gained by many aspects, including the use of small and very sparse networks, where the weights of the recurrent units are left untrained under the stability condition introduced in this work. This can be viewed as a way to study the intrinsic power of the architecture of a deep GNN, and also to provide insights for the set-up of more complex fully-trained models. Through experimental results, we show that even without training of the recurrent connections, the architecture of small deep GNN is surprisingly able to achieve or improve the state-of-the-art performance on a significant set of tasks in the field of graphs classification. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08941v1 |
| https://arxiv.org/pdf/1911.08941v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-deep-graph-neural-networks |
| Repo | |
| Framework | |
Using learned optimizers to make models robust to input noise
| Title | Using learned optimizers to make models robust to input noise |
| Authors | Luke Metz, Niru Maheswaranathan, Jonathon Shlens, Jascha Sohl-Dickstein, Ekin D. Cubuk |
| Abstract | State-of-the art vision models can achieve superhuman performance on image classification tasks when testing and training data come from the same distribution. However, when models are tested on corrupted images (e.g. due to scale changes, translations, or shifts in brightness or contrast), performance degrades significantly. Here, we explore the possibility of meta-training a learned optimizer that can train image classification models such that they are robust to common image corruptions. Specifically, we are interested training models that are more robust to noise distributions not present in the training data. We find that a learned optimizer meta-trained to produce models which are robust to Gaussian noise trains models that are more robust to Gaussian noise at other scales compared to traditional optimizers like Adam. The effect of meta-training is more complicated when targeting a more general set of noise distributions, but led to improved performance on half of held-out corruption tasks. Our results suggest that meta-learning provides a novel approach for studying and improving the robustness of deep learning models. |
| Tasks | Image Classification, Meta-Learning |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03367v1 |
| https://arxiv.org/pdf/1906.03367v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-learned-optimizers-to-make-models |
| Repo | |
| Framework | |
Computationally efficient versions of conformal predictive distributions
| Title | Computationally efficient versions of conformal predictive distributions |
| Authors | Vladimir Vovk, Ivan Petej, Ilia Nouretdinov, Valery Manokhin, Alex Gammerman |
| Abstract | Conformal predictive systems are a recent modification of conformal predictors that output, in regression problems, probability distributions for labels of test observations rather than set predictions. The extra information provided by conformal predictive systems may be useful, e.g., in decision making problems. Conformal predictive systems inherit the relative computational inefficiency of conformal predictors. In this paper we discuss two computationally efficient versions of conformal predictive systems, which we call split conformal predictive systems and cross-conformal predictive systems. The main advantage of split conformal predictive systems is their guaranteed validity, whereas for cross-conformal predictive systems validity only holds empirically and in the absence of excessive randomization. The main advantage of cross-conformal predictive systems is their greater predictive efficiency. |
| Tasks | Decision Making |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00941v1 |
| https://arxiv.org/pdf/1911.00941v1.pdf | |
| PWC | https://paperswithcode.com/paper/computationally-efficient-versions-of |
| Repo | |
| Framework | |
