Paper Group ANR 1042
Probabilistic Matrix Factorization with Personalized Differential Privacy. Extended pipeline for content-based feature engineering in music genre recognition. Neural Program Search: Solving Programming Tasks from Description and Examples. On the self-similarity of line segments in decaying homogeneous isotropic turbulence. Semi-Supervised Learning …
Probabilistic Matrix Factorization with Personalized Differential Privacy
| Title | Probabilistic Matrix Factorization with Personalized Differential Privacy |
| Authors | Shun Zhang, Laixiang Liu, Zhili Chen, Hong Zhong |
| Abstract | Probabilistic matrix factorization (PMF) plays a crucial role in recommendation systems. It requires a large amount of user data (such as user shopping records and movie ratings) to predict personal preferences, and thereby provides users high-quality recommendation services, which expose the risk of leakage of user privacy. Differential privacy, as a provable privacy protection framework, has been applied widely to recommendation systems. It is common that different individuals have different levels of privacy requirements on items. However, traditional differential privacy can only provide a uniform level of privacy protection for all users. In this paper, we mainly propose a probabilistic matrix factorization recommendation scheme with personalized differential privacy (PDP-PMF). It aims to meet users’ privacy requirements specified at the item-level instead of giving the same level of privacy guarantees for all. We then develop a modified sampling mechanism (with bounded differential privacy) for achieving PDP. We also perform a theoretical analysis of the PDP-PMF scheme and demonstrate the privacy of the PDP-PMF scheme. In addition, we implement the probabilistic matrix factorization schemes both with traditional and with personalized differential privacy (DP-PMF, PDP-PMF) and compare them through a series of experiments. The results show that the PDP-PMF scheme performs well on protecting the privacy of each user and its recommendation quality is much better than the DP-PMF scheme. |
| Tasks | Recommendation Systems |
| Published | 2018-10-19 |
| URL | http://arxiv.org/abs/1810.08509v1 |
| http://arxiv.org/pdf/1810.08509v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-matrix-factorization-with |
| Repo | |
| Framework | |
Extended pipeline for content-based feature engineering in music genre recognition
| Title | Extended pipeline for content-based feature engineering in music genre recognition |
| Authors | Tina Raissi, Alessandro Tibo, Paolo Bientinesi |
| Abstract | We present a feature engineering pipeline for the construction of musical signal characteristics, to be used for the design of a supervised model for musical genre identification. The key idea is to extend the traditional two-step process of extraction and classification with additive stand-alone phases which are no longer organized in a waterfall scheme. The whole system is realized by traversing backtrack arrows and cycles between various stages. In order to give a compact and effective representation of the features, the standard early temporal integration is combined with other selection and extraction phases: on the one hand, the selection of the most meaningful characteristics based on information gain, and on the other hand, the inclusion of the nonlinear correlation between this subset of features, determined by an autoencoder. The results of the experiments conducted on GTZAN dataset reveal a noticeable contribution of this methodology towards the model’s performance in classification task. |
| Tasks | Feature Engineering, Music Genre Recognition |
| Published | 2018-05-12 |
| URL | http://arxiv.org/abs/1805.05324v1 |
| http://arxiv.org/pdf/1805.05324v1.pdf | |
| PWC | https://paperswithcode.com/paper/extended-pipeline-for-content-based-feature |
| Repo | |
| Framework | |
Neural Program Search: Solving Programming Tasks from Description and Examples
| Title | Neural Program Search: Solving Programming Tasks from Description and Examples |
| Authors | Illia Polosukhin, Alexander Skidanov |
| Abstract | We present a Neural Program Search, an algorithm to generate programs from natural language description and a small number of input/output examples. The algorithm combines methods from Deep Learning and Program Synthesis fields by designing rich domain-specific language (DSL) and defining efficient search algorithm guided by a Seq2Tree model on it. To evaluate the quality of the approach we also present a semi-synthetic dataset of descriptions with test examples and corresponding programs. We show that our algorithm significantly outperforms a sequence-to-sequence model with attention baseline. |
| Tasks | Program Synthesis |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.04335v1 |
| http://arxiv.org/pdf/1802.04335v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-program-search-solving-programming |
| Repo | |
| Framework | |
On the self-similarity of line segments in decaying homogeneous isotropic turbulence
| Title | On the self-similarity of line segments in decaying homogeneous isotropic turbulence |
| Authors | Michael Gauding, Lipo Wang, Jens Henrik Goebbert, Mathis Bode, Luminita Danaila, Emilien Varea |
| Abstract | The self-similarity of a passive scalar in homogeneous isotropic decaying turbulence is investigated by the method of line segments (M. Gauding et al., Physics of Fluids 27.9 (2015): 095102). The analysis is based on a highly resolved direct numerical simulation of decaying turbulence. The method of line segments is used to perform a decomposition of the scalar field into smaller sub-units based on the extremal points of the scalar along a straight line. These sub-units (the so-called line segments) are parameterized by their length $\ell$ and the difference $\Delta\phi$ of the scalar field between the ending points. Line segments can be understood as thin local convective-diffusive structures in which diffusive processes are enhanced by compressive strain. From DNS, it is shown that the marginal distribution function of the length~$\ell$ assumes complete self-similarity when re-scaled by the mean length $\ell_m$. The joint statistics of $\Delta\phi$ and $\ell$, from which the local gradient $g=\Delta\phi/\ell$ can be defined, play an important role in understanding the turbulence mixing and flow structure. Large values of $g$ occur at a small but finite length scale. Statistics of $g$ are characterized by rare but strong deviations that exceed the standard deviation by more than one order of magnitude. It is shown that these events break complete self-similarity of line segments, which confirms the standard paradigm of turbulence that intense events (which are known as internal intermittency) are not self-similar. |
| Tasks | |
| Published | 2018-09-20 |
| URL | http://arxiv.org/abs/1809.07539v1 |
| http://arxiv.org/pdf/1809.07539v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-self-similarity-of-line-segments-in |
| Repo | |
| Framework | |
Semi-Supervised Learning with Declaratively Specified Entropy Constraints
| Title | Semi-Supervised Learning with Declaratively Specified Entropy Constraints |
| Authors | Haitian Sun, William W. Cohen, Lidong Bing |
| Abstract | We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL). The proposed method can be used to specify ensembles of semi-supervised learning, as well as agreement constraints and entropic regularization constraints between these learners, and can be used to model both well-known heuristics such as co-training and novel domain-specific heuristics. In addition to representing individual SSL heuristics, we show that multiple heuristics can also be automatically combined using Bayesian optimization methods. We show consistent improvements on a suite of well-studied SSL benchmarks, including a new state-of-the-art result on a difficult relation extraction task. |
| Tasks | Relation Extraction |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.09238v2 |
| http://arxiv.org/pdf/1804.09238v2.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-with-declaratively |
| Repo | |
| Framework | |
Handling Nominals and Inverse Roles using Algebraic Reasoning
| Title | Handling Nominals and Inverse Roles using Algebraic Reasoning |
| Authors | Humaira Farid, Volker Haarslev |
| Abstract | This paper presents a novel SHOI tableau calculus which incorporates algebraic reasoning for deciding ontology consistency. Numerical restrictions imposed by nominals, existential and universal restrictions are encoded into a set of linear inequalities. Column generation and branch-and-price algorithms are used to solve these inequalities. Our preliminary experiments indicate that this calculus performs better on SHOI ontologies than standard tableau methods. |
| Tasks | |
| Published | 2018-10-01 |
| URL | http://arxiv.org/abs/1810.00916v1 |
| http://arxiv.org/pdf/1810.00916v1.pdf | |
| PWC | https://paperswithcode.com/paper/handling-nominals-and-inverse-roles-using |
| Repo | |
| Framework | |
Predicting Gender from Iris Texture May Be Harder Than It Seems
| Title | Predicting Gender from Iris Texture May Be Harder Than It Seems |
| Authors | Andrey Kuehlkamp, Kevin Bowyer |
| Abstract | Predicting gender from iris images has been reported by several researchers as an application of machine learning in biometrics. Recent works on this topic have suggested that the preponderance of the gender cues is located in the periocular region rather than in the iris texture itself. This paper focuses on teasing out whether the information for gender prediction is in the texture of the iris stroma, the periocular region, or both. We present a larger dataset for gender from iris, and evaluate gender prediction accuracy using linear SVM and CNN, comparing hand-crafted and deep features. We use probabilistic occlusion masking to gain insight on the problem. Results suggest the discriminative power of the iris texture for gender is weaker than previously thought, and that the gender-related information is primarily in the periocular region. |
| Tasks | Gender Prediction |
| Published | 2018-11-25 |
| URL | http://arxiv.org/abs/1811.10066v1 |
| http://arxiv.org/pdf/1811.10066v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-gender-from-iris-texture-may-be |
| Repo | |
| Framework | |
RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory
| Title | RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory |
| Authors | Mohammad Hossein Samavatian, Anys Bacha, Li Zhou, Radu Teodorescu |
| Abstract | Recurrent Neural Networks (RNNs) are an important class of neural networks designed to retain and incorporate context into current decisions. RNNs are particularly well suited for machine learning problems in which context is important, such as speech recognition or language translation. This work presents RNNFast, a hardware accelerator for RNNs that leverages an emerging class of non-volatile memory called domain-wall memory (DWM). We show that DWM is very well suited for RNN acceleration due to its very high density and low read/write energy. At the same time, the sequential nature of input/weight processing of RNNs mitigates one of the downsides of DWM, which is the linear (rather than constant) data access time. RNNFast is very efficient and highly scalable, with flexible mapping of logical neurons to RNN hardware blocks. The basic hardware primitive, the RNN processing element (PE) includes custom DWM-based multiplication, sigmoid and tanh units for high density and low-energy. The accelerator is designed to minimize data movement by closely interleaving DWM storage and computation. We compare our design with a state-of-the-art GPGPU and find 21.8x better performance with 70x lower energy. |
| Tasks | Speech Recognition |
| Published | 2018-11-07 |
| URL | https://arxiv.org/abs/1812.07609v1 |
| https://arxiv.org/pdf/1812.07609v1.pdf | |
| PWC | https://paperswithcode.com/paper/rnnfast-an-accelerator-for-recurrent-neural |
| Repo | |
| Framework | |
Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks
| Title | Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks |
| Authors | Li Wang, Ting Liu, Bing Wang, Xulei Yang, Gang Wang |
| Abstract | Recently, deep learning has achieved very promising results in visual object tracking. Deep neural networks in existing tracking methods require a lot of training data to learn a large number of parameters. However, training data is not sufficient for visual object tracking as annotations of a target object are only available in the first frame of a test sequence. In this paper, we propose to learn hierarchical features for visual object tracking by using tree structure based Recursive Neural Networks (RNN), which have fewer parameters than other deep neural networks, e.g. Convolutional Neural Networks (CNN). First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence. Tree structure over local patches of an exemplar region is randomly generated by using a bottom-up greedy search strategy. Given the learned RNN parameters, we create two dictionaries regarding target regions and corresponding local patches based on the learned hierarchical features from both top and leaf nodes of multiple random trees. In each of the subsequent frames, we conduct sparse dictionary coding on all candidates to select the best candidate as the new target location. In addition, we online update two dictionaries to handle appearance changes of target objects. Experimental results demonstrate that our feature learning algorithm can significantly improve tracking performance on benchmark datasets. |
| Tasks | Object Tracking, Visual Object Tracking |
| Published | 2018-01-06 |
| URL | http://arxiv.org/abs/1801.02021v1 |
| http://arxiv.org/pdf/1801.02021v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-hierarchical-features-for-visual |
| Repo | |
| Framework | |
Convolutional Set Matching for Graph Similarity
| Title | Convolutional Set Matching for Graph Similarity |
| Authors | Yunsheng Bai, Hao Ding, Yizhou Sun, Wei Wang |
| Abstract | We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs. As the core operation of graph similarity search, pairwise graph similarity computation is a challenging problem due to the NP-hard nature of computing many graph distance/similarity metrics. We demonstrate our model using the Graph Edit Distance (GED) as the example metric. Experiments on three real graph datasets demonstrate that our model achieves the state-of-the-art performance on graph similarity search. |
| Tasks | Graph Similarity |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.10866v3 |
| http://arxiv.org/pdf/1810.10866v3.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-set-matching-for-graph |
| Repo | |
| Framework | |
Large Margin Neural Language Model
| Title | Large Margin Neural Language Model |
| Authors | Jiaji Huang, Yi Li, Wei Ping, Liang Huang |
| Abstract | We propose a large margin criterion for training neural language models. Conventionally, neural language models are trained by minimizing perplexity (PPL) on grammatical sentences. However, we demonstrate that PPL may not be the best metric to optimize in some tasks, and further propose a large margin formulation. The proposed method aims to enlarge the margin between the “good” and “bad” sentences in a task-specific sense. It is trained end-to-end and can be widely applied to tasks that involve re-scoring of generated text. Compared with minimum-PPL training, our method gains up to 1.1 WER reduction for speech recognition and 1.0 BLEU increase for machine translation. |
| Tasks | Language Modelling, Machine Translation, Speech Recognition |
| Published | 2018-08-27 |
| URL | http://arxiv.org/abs/1808.08987v1 |
| http://arxiv.org/pdf/1808.08987v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-margin-neural-language-model |
| Repo | |
| Framework | |
Bound and Conquer: Improving Triangulation by Enforcing Consistency
| Title | Bound and Conquer: Improving Triangulation by Enforcing Consistency |
| Authors | Adam Scholefield, Alireza Ghasemi, Martin Vetterli |
| Abstract | We study the accuracy of triangulation in multi-camera systems with respect to the number of cameras. We show that, under certain conditions, the optimal achievable reconstruction error decays quadratically as more cameras are added to the system. Furthermore, we analyse the error decay-rate of major state-of-the-art algorithms with respect to the number of cameras. To this end, we introduce the notion of consistency for triangulation, and show that consistent reconstruction algorithms achieve the optimal quadratic decay, which is asymptotically faster than some other methods. Finally, we present simulations results supporting our findings. Our simulations have been implemented in MATLAB and the resulting code is available in the supplementary material. |
| Tasks | |
| Published | 2018-04-27 |
| URL | http://arxiv.org/abs/1804.10448v1 |
| http://arxiv.org/pdf/1804.10448v1.pdf | |
| PWC | https://paperswithcode.com/paper/bound-and-conquer-improving-triangulation-by |
| Repo | |
| Framework | |
Approximation and Estimation for High-Dimensional Deep Learning Networks
| Title | Approximation and Estimation for High-Dimensional Deep Learning Networks |
| Authors | Andrew R. Barron, Jason M. Klusowski |
| Abstract | It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this? The best available bounds on their metric entropy and associated complexity measures are essentially linear in the number of parameters, which is inadequate to explain this phenomenon. Here we examine the statistical risk (mean squared predictive error) of multi-layer networks with $\ell^1$-type controls on their parameters and with ramp activation functions (also called lower-rectified linear units). In this setting, the risk is shown to be upper bounded by $[(L^3 \log d)/n]^{1/2}$, where $d$ is the input dimension to each layer, $L$ is the number of layers, and $n$ is the sample size. In this way, the input dimension can be much larger than the sample size and the estimator can still be accurate, provided the target function has such $\ell^1$ controls and that the sample size is at least moderately large compared to $L^3\log d$. The heart of the analysis is the development of a sampling strategy that demonstrates the accuracy of a sparse covering of deep ramp networks. Lower bounds show that the identified risk is close to being optimal. |
| Tasks | |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03090v2 |
| http://arxiv.org/pdf/1809.03090v2.pdf | |
| PWC | https://paperswithcode.com/paper/approximation-and-estimation-for-high |
| Repo | |
| Framework | |
Fast Parametric Learning with Activation Memorization
| Title | Fast Parametric Learning with Activation Memorization |
| Authors | Jack W Rae, Chris Dyer, Peter Dayan, Timothy P Lillicrap |
| Abstract | Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, such as language modelling, this can become a performance bottleneck. One potential remedy is to augment the network with a fast-learning non-parametric model which stores recent activations and class labels into an external memory. We explore a simplified architecture where we treat a subset of the model parameters as fast memory stores. This can help retain information over longer time intervals than a traditional memory, and does not require additional space or compute. In the case of image classification, we display faster binding of novel classes on an Omniglot image curriculum task. We also show improved performance for word-based language models on news reports (GigaWord), books (Project Gutenberg) and Wikipedia articles (WikiText-103) — the latter achieving a state-of-the-art perplexity of 29.2. |
| Tasks | Image Classification, Language Modelling, Omniglot |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10049v1 |
| http://arxiv.org/pdf/1803.10049v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-parametric-learning-with-activation |
| Repo | |
| Framework | |
Deformable Stacked Structure for Named Entity Recognition
| Title | Deformable Stacked Structure for Named Entity Recognition |
| Authors | Shuyang Cao, Xipeng Qiu, Xuanjing Huang |
| Abstract | Neural architecture for named entity recognition has achieved great success in the field of natural language processing. Currently, the dominating architecture consists of a bi-directional recurrent neural network (RNN) as the encoder and a conditional random field (CRF) as the decoder. In this paper, we propose a deformable stacked structure for named entity recognition, in which the connections between two adjacent layers are dynamically established. We evaluate the deformable stacked structure by adapting it to different layers. Our model achieves the state-of-the-art performances on the OntoNotes dataset. |
| Tasks | Named Entity Recognition |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.08730v2 |
| http://arxiv.org/pdf/1809.08730v2.pdf | |
| PWC | https://paperswithcode.com/paper/deformable-stacked-structure-for-named-entity |
| Repo | |
| Framework | |
