Paper Group ANR 765
A generic rule-based system for clinical trial patient selection. Recommendation Engine for Lower Interest Borrowing on Peer to Peer Lending (P2PL) Platform. Teacher-Student Framework Enhanced Multi-domain Dialogue Generation. Composite Event Recognition for Maritime Monitoring. Inferring the dynamics of oscillatory systems using recurrent neural n …
A generic rule-based system for clinical trial patient selection
| Title | A generic rule-based system for clinical trial patient selection |
| Authors | Jianlin Shi, Kevin Graves, John F. Hurdle |
| Abstract | The n2c2 2018 Challenge task 1 aimed to identify patients who meet lists of heterogeneous inclusion/exclusion criteria for a hypothetical clinical trial. We demonstrate a generic rule-based natural language pipeline can support this task with decent performance (the average F1 score on the test set is 0.89, ranked the 8th out of 45 teams ). |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06860v1 |
| https://arxiv.org/pdf/1907.06860v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generic-rule-based-system-for-clinical |
| Repo | |
| Framework | |
Recommendation Engine for Lower Interest Borrowing on Peer to Peer Lending (P2PL) Platform
| Title | Recommendation Engine for Lower Interest Borrowing on Peer to Peer Lending (P2PL) Platform |
| Authors | Ke Ren, Avinash Malik |
| Abstract | Online Peer to Peer Lending (P2PL) systems connect lenders and borrowers directly, thereby making it convenient to borrow and lend money without intermediaries such as banks. Many recommendation systems have been developed for lenders to achieve higher interest rates and avoid defaulting loans. However, there has not been much research in developing recommendation systems to help borrowers make wise decisions. On P2PL platforms, borrowers can either apply for bidding loans, where the interest rate is determined by lenders bidding on a loan or traditional loans where the P2PL platform determines the interest rate. Different borrower grades – determining the credit worthiness of borrowers get different interest rates via these two mechanisms. Hence, it is essential to determine which type of loans borrowers should apply for. In this paper, we build a recommendation system that recommends to any new borrower the type of loan they should apply for. Using our recommendation system, any borrower can achieve lowered interest rates with a higher likelihood of getting funded. |
| Tasks | Recommendation Systems |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.11634v1 |
| https://arxiv.org/pdf/1907.11634v1.pdf | |
| PWC | https://paperswithcode.com/paper/recommendation-engine-for-lower-interest |
| Repo | |
| Framework | |
Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
| Title | Teacher-Student Framework Enhanced Multi-domain Dialogue Generation |
| Authors | Shuke Peng, Xinjing Huang, Zehao Lin, Feng Ji, Haiqing Chen, Yin Zhang |
| Abstract | Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-defined features as dialogue states and apply a state tracker to extract these features. However, the performance of such a system is limited by the error propagation of a state tracker. In this paper, we propose a dialogue generation model that needs no external state trackers and still benefits from human-labeled semantic data. By using a teacher-student framework, several teacher models are firstly trained in their individual domains, learn dialogue policies from labeled states. And then the learned knowledge and experience are merged and transferred to a universal student model, which takes raw utterance as its input. Experiments show that the dialogue system trained under our framework outperforms the one uses a belief tracker. |
| Tasks | Dialogue Generation |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07137v1 |
| https://arxiv.org/pdf/1908.07137v1.pdf | |
| PWC | https://paperswithcode.com/paper/teacher-student-framework-enhanced-multi |
| Repo | |
| Framework | |
Composite Event Recognition for Maritime Monitoring
| Title | Composite Event Recognition for Maritime Monitoring |
| Authors | Manolis Pitsikalis, Alexander Artikis, Richard Dreo, Cyril Ray, Elena Camossi, Anne-Laure Jousselme |
| Abstract | Maritime monitoring systems support safe shipping as they allow for the real-time detection of dangerous, suspicious and illegal vessel activities. We present such a system using the Run-Time Event Calculus, a composite event recognition system with formal, declarative semantics. For effective recognition, we developed a library of maritime patterns in close collaboration with domain experts. We present a thorough evaluation of the system and the patterns both in terms of predictive accuracy and computational efficiency, using real-world datasets of vessel position streams and contextual geographical information. |
| Tasks | |
| Published | 2019-03-07 |
| URL | https://arxiv.org/abs/1903.03078v3 |
| https://arxiv.org/pdf/1903.03078v3.pdf | |
| PWC | https://paperswithcode.com/paper/composite-event-recognition-for-maritime |
| Repo | |
| Framework | |
Inferring the dynamics of oscillatory systems using recurrent neural networks
| Title | Inferring the dynamics of oscillatory systems using recurrent neural networks |
| Authors | Rok Cestnik, Markus Abel |
| Abstract | We investigate the predictive power of recurrent neural networks for oscillatory systems not only on the attractor, but in its vicinity as well. For this we consider systems perturbed by an external force. This allows us to not merely predict the time evolution of the system, but also study its dynamical properties, such as bifurcations, dynamical response curves, characteristic exponents etc. It is shown that they can be effectively estimated even in some regions of the state space where no input data were given. We consider several different oscillatory examples, including self-sustained, excitatory, time-delay and chaotic systems. Furthermore, with a statistical analysis we assess the amount of training data required for effective inference for two common recurrent neural network cells, the long short-term memory and the gated recurrent unit. |
| Tasks | |
| Published | 2019-04-04 |
| URL | https://arxiv.org/abs/1904.03026v2 |
| https://arxiv.org/pdf/1904.03026v2.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-the-dynamics-of-oscillatory-systems |
| Repo | |
| Framework | |
The advantages of multiple classes for reducing overfitting from test set reuse
| Title | The advantages of multiple classes for reducing overfitting from test set reuse |
| Authors | Vitaly Feldman, Roy Frostig, Moritz Hardt |
| Abstract | Excessive reuse of holdout data can lead to overfitting. However, there is little concrete evidence of significant overfitting due to holdout reuse in popular multiclass benchmarks today. Known results show that, in the worst-case, revealing the accuracy of $k$ adaptively chosen classifiers on a data set of size $n$ allows to create a classifier with bias of $\Theta(\sqrt{k/n})$ for any binary prediction problem. We show a new upper bound of $\tilde O(\max{\sqrt{k\log(n)/(mn)},k/n})$ on the worst-case bias that any attack can achieve in a prediction problem with $m$ classes. Moreover, we present an efficient attack that achieve a bias of $\Omega(\sqrt{k/(m^2 n)})$ and improves on previous work for the binary setting ($m=2$). We also present an inefficient attack that achieves a bias of $\tilde\Omega(k/n)$. Complementing our theoretical work, we give new practical attacks to stress-test multiclass benchmarks by aiming to create as large a bias as possible with a given number of queries. Our experiments show that the additional uncertainty of prediction with a large number of classes indeed mitigates the effect of our best attacks. Our work extends developments in understanding overfitting due to adaptive data analysis to multiclass prediction problems. It also bears out the surprising fact that multiclass prediction problems are significantly more robust to overfitting when reusing a test (or holdout) dataset. This offers an explanation as to why popular multiclass prediction benchmarks, such as ImageNet, may enjoy a longer lifespan than what intuition from literature on binary classification suggests. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10360v1 |
| https://arxiv.org/pdf/1905.10360v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-advantages-of-multiple-classes-for |
| Repo | |
| Framework | |
Detection of Shilling Attack Based on T-distribution on the Dynamic Time Intervals in Recommendation Systems
| Title | Detection of Shilling Attack Based on T-distribution on the Dynamic Time Intervals in Recommendation Systems |
| Authors | Wanqiao Yuan, Yingyuan Xiao, Xu Jiao, Wenguang Zheng, Zihao Ling |
| Abstract | With the development of information technology and the Internet, recommendation systems have become an important means to solve the problem of information overload. However, recommendation system is greatly fragile as it relies heavily on behavior data of users, which makes it very easy for a host of malicious merchants to inject shilling attacks in order to manipulate the recommendation results. Some papers on shilling attack have proposed the detection methods, whether based on false user profiles or abnormal items, but their detection rate, false alarm rate, universality, and time overhead need to be further improved. In this paper, we propose a new item anomaly detection method, through T-distribution technology based on Dynamic Time Intervals. First of all, based on the characteristics of shilling attack quickness (Attackers inject a large number of fake profiles in a short period in order to save costs), we use dynamic time interval method to divide the rating history of item into multiple time windows. Then, we use the T-distribution to detect the exception windows. By conducting extensive experiments on a dataset that accords with real-life situations and comparing it to currently outstanding methods, our proposed approach has a higher detection rate, lower false alarm rate and smaller time overhead to the different attack models and filler sizes. |
| Tasks | Anomaly Detection, Recommendation Systems |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06967v1 |
| https://arxiv.org/pdf/1908.06967v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-of-shilling-attack-based-on-t |
| Repo | |
| Framework | |
Towards a practical $k$-dimensional Weisfeiler-Leman algorithm
| Title | Towards a practical $k$-dimensional Weisfeiler-Leman algorithm |
| Authors | Christopher Morris, Petra Mutzel |
| Abstract | The $k$-dimensional Weisfeiler-Leman algorithm is a well-known heuristic for the graph isomorphism problem. Moreover, it recently emerged as a powerful tool for supervised graph classification. The algorithm iteratively partitions the set of $k$-tuples, defined over the set of vertices of a graph, by considering neighboring $k$-tuples. Here, we propose a \new{local} variant which considers a subset of the original neighborhood in each iteration step. The cardinality of this local neighborhood, unlike the original one, only depends on the sparsity of the graph. We show that the local variant has at least the same power as the original algorithm in terms of distinguishing non-isomorphic graphs. To demonstrate the practical utility of our local variant, we apply it to supervised graph classification. Our experimental study shows that our local algorithm leads to improved running times and classification accuracies on established benchmark datasets. |
| Tasks | Graph Classification |
| Published | 2019-04-02 |
| URL | https://arxiv.org/abs/1904.01543v2 |
| https://arxiv.org/pdf/1904.01543v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-practical-k-dimensional-weisfeiler |
| Repo | |
| Framework | |
Dialogue Transformers
| Title | Dialogue Transformers |
| Authors | Vladimir Vlasov, Johannes E. M. Mosig, Alan Nichol |
| Abstract | We introduce a dialogue policy based on a transformer architecture, where the self-attention mechanism operates over the sequence of dialogue turns. Recent work has used hierarchical recurrent neural networks to encode multiple utterances in a dialogue context, but we argue that a pure self-attention mechanism is more suitable. By default, an RNN assumes that every item in a sequence is relevant for producing an encoding of the full sequence, but a single conversation can consist of multiple overlapping discourse segments as speakers interleave multiple topics. A transformer picks which turns to include in its encoding of the current dialogue state, and is naturally suited to selectively ignoring or attending to dialogue history. We compare the performance of the Transformer Embedding Dialogue (TED) policy to an LSTM and to the REDP, which was specifically designed to overcome this limitation of RNNs. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00486v2 |
| https://arxiv.org/pdf/1910.00486v2.pdf | |
| PWC | https://paperswithcode.com/paper/dialogue-transformers |
| Repo | |
| Framework | |
Do Co-purchases Reveal Preferences? Explainable Recommendation with Attribute Networks
| Title | Do Co-purchases Reveal Preferences? Explainable Recommendation with Attribute Networks |
| Authors | Guannan Liu, Liang Zhang |
| Abstract | With the prosperity of business intelligence, recommender systems have evolved into a new stage that we not only care about what to recommend, but why it is recommended. Explainability of recommendations thus emerges as a focal point of research and becomes extremely desired in e-commerce. Existent studies along this line often exploit item attributes and correlations from different perspectives, but they yet lack an effective way to combine both types of information for deep learning of personalized interests. In light of this, we propose a novel graph structure, \emph{attribute network}, based on both items’ co-purchase network and important attributes. A novel neural model called \emph{eRAN} is then proposed to generate recommendations from attribute networks with explainability and cold-start capability. Specifically, eRAN first maps items connected in attribute networks to low-dimensional embedding vectors through a deep autoencoder, and then an attention mechanism is applied to model the attractions of attributes to users, from which personalized item representation can be derived. Moreover, a pairwise ranking loss is constructed into eRAN to improve recommendations, with the assumption that item pairs co-purchased by a user should be more similar than those non-paired with negative sampling in personalized view. Experiments on real-world datasets demonstrate the effectiveness of our method compared with some state-of-the-art competitors. In particular, eRAN shows its unique abilities in recommending cold-start items with higher accuracy, as well as in understanding user preferences underlying complicated co-purchasing behaviors. |
| Tasks | Recommendation Systems |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05928v1 |
| https://arxiv.org/pdf/1908.05928v1.pdf | |
| PWC | https://paperswithcode.com/paper/do-co-purchases-reveal-preferences |
| Repo | |
| Framework | |
Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability
| Title | Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability |
| Authors | Benjamin A. Toms, Elizabeth A. Barnes, Imme Ebert-Uphoff |
| Abstract | Neural networks have become increasingly prevalent within the geosciences for applications ranging from numerical model parameterizations to the prediction of extreme weather. A common limitation of neural networks has been the lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks have typically been used within the geosciences to accurately identify a desired output given a set of inputs, with the interpretation of what the network learns being used - if used at all - as a secondary metric to ensure the network is making the right decision for the right reason. Network interpretation techniques have become more advanced in recent years, however, and we therefore propose that the ultimate objective of using a neural network can also be the interpretation of what the network has learned rather than the output itself. We show that the interpretation of a neural network can enable the discovery of scientifically meaningful connections within geoscientific data. By training neural networks to use one or more components of the earth system to identify another, interpretation methods can be used to gain scientific insights into how and why the two components are related. In particular, we use two methods for neural network interpretation. These methods project the decision pathways of a network back onto the original input dimensions, and are called “optimal input” and layerwise relevance propagation (LRP). We then show how these interpretation techniques can be used to reliably infer scientifically meaningful information from neural networks by applying them to common climate patterns. These results suggest that combining interpretable neural networks with novel scientific hypotheses will open the door to many new avenues in neural network-related geoscience research. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01752v1 |
| https://arxiv.org/pdf/1912.01752v1.pdf | |
| PWC | https://paperswithcode.com/paper/physically-interpretable-neural-networks-for |
| Repo | |
| Framework | |
Deformable kernel networks for guided depth map upsampling
| Title | Deformable kernel networks for guided depth map upsampling |
| Authors | Beomjun Kim, Jean Ponce, Bumsub Ham |
| Abstract | We address the problem of upsampling a low-resolution (LR) depth map using a registered high-resolution (HR) color image of the same scene. Previous methods based on convolutional neural networks (CNNs) combine nonlinear activations of spatially-invariant kernels to estimate structural details from LR depth and HR color images, and regress upsampling results directly from the networks. In this paper, we revisit the weighted averaging process that has been widely used to transfer structural details from hand-crafted visual features to LR depth maps. We instead learn explicitly sparse and spatially-variant kernels for this task. To this end, we propose a CNN architecture and its efficient implementation, called the deformable kernel network (DKN), that outputs sparse sets of neighbors and the corresponding weights adaptively for each pixel. We also propose a fast version of DKN (FDKN) that runs about 17 times faster (0.01 seconds for a HR image of size 640 x 480). Experimental results on standard benchmarks demonstrate the effectiveness of our approach. In particular, we show that the weighted averaging process with 3 x 3 kernels (i.e., aggregating 9 samples sparsely chosen) outperforms the state of the art by a significant margin. |
| Tasks | |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1903.11286v1 |
| http://arxiv.org/pdf/1903.11286v1.pdf | |
| PWC | https://paperswithcode.com/paper/deformable-kernel-networks-for-guided-depth |
| Repo | |
| Framework | |
Disentangled Image Matting
| Title | Disentangled Image Matting |
| Authors | Shaofan Cai, Xiaoshuai Zhang, Haoqiang Fan, Haibin Huang, Jiangyu Liu, Jiaming Liu, Jiaying Liu, Jue Wang, Jian Sun |
| Abstract | Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap. In this paper, we argue that directly estimating the alpha matte from a coarse trimap is a major limitation of previous methods, as this practice tries to address two difficult and inherently different problems at the same time: identifying true blending pixels inside the trimap region, and estimate accurate alpha values for them. We propose AdaMatting, a new end-to-end matting framework that disentangles this problem into two sub-tasks: trimap adaptation and alpha estimation. Trimap adaptation is a pixel-wise classification problem that infers the global structure of the input image by identifying definite foreground, background, and semi-transparent image regions. Alpha estimation is a regression problem that calculates the opacity value of each blended pixel. Our method separately handles these two sub-tasks within a single deep convolutional neural network (CNN). Extensive experiments show that AdaMatting has additional structure awareness and trimap fault-tolerance. Our method achieves the state-of-the-art performance on Adobe Composition-1k dataset both qualitatively and quantitatively. It is also the current best-performing method on the alphamatting.com online evaluation for all commonly-used metrics. |
| Tasks | Image Matting |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04686v1 |
| https://arxiv.org/pdf/1909.04686v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangled-image-matting |
| Repo | |
| Framework | |
Egocentric Bias and Doubt in Cognitive Agents
| Title | Egocentric Bias and Doubt in Cognitive Agents |
| Authors | Nanda Kishore Sreenivas, Shrisha Rao |
| Abstract | Modeling social interactions based on individual behavior has always been an area of interest, but prior literature generally presumes rational behavior. Thus, such models may miss out on capturing the effects of biases humans are susceptible to. This work presents a method to model egocentric bias, the real-life tendency to emphasize one’s own opinion heavily when presented with multiple opinions. We use a symmetric distribution centered at an agent’s own opinion, as opposed to the Bounded Confidence (BC) model used in prior work. We consider a game of iterated interactions where an agent cooperates based on its opinion about an opponent. Our model also includes the concept of domain-based self-doubt, which varies as the interaction succeeds or not. An increase in doubt makes an agent reduce its egocentricity in subsequent interactions, thus enabling the agent to learn reactively. The agent system is modeled with factions not having a single leader, to overcome some of the issues associated with leader-follower factions. We find that agents belonging to factions perform better than individual agents. We observe that an intermediate level of egocentricity helps the agent perform at its best, which concurs with conventional wisdom that neither overconfidence nor low self-esteem brings benefits. |
| Tasks | |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.03443v1 |
| http://arxiv.org/pdf/1903.03443v1.pdf | |
| PWC | https://paperswithcode.com/paper/egocentric-bias-and-doubt-in-cognitive-agents |
| Repo | |
| Framework | |
On the convergence of gradient descent for two layer neural networks
| Title | On the convergence of gradient descent for two layer neural networks |
| Authors | Lei Li |
| Abstract | It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing works, we investigate the gradient descent method for training two-layer neural networks for approximating some target continuous functions. By making use the generic chaining technique from probability theory, we show that gradient descent can yield an exponential convergence rate, while the width of the neural networks needed is independent of the size of the training data. The result also implies some strong approximation ability of the two-layer neural networks without curse of dimensionality. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13671v3 |
| https://arxiv.org/pdf/1909.13671v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-convergence-of-gradient-descent-for |
| Repo | |
| Framework | |
