January 30, 2020

3248 words 16 mins read

Paper Group ANR 333

DeepTrax: Embedding Graphs of Financial Transactions. Helen: Maliciously Secure Coopetitive Learning for Linear Models. Clustering with Distributed Data. Linking Graph Entities with Multiplicity and Provenance. Centroid-based deep metric learning for speaker recognition. Fast Weakly Supervised Action Segmentation Using Mutual Consistency. Proving D …

DeepTrax: Embedding Graphs of Financial Transactions


Title	DeepTrax: Embedding Graphs of Financial Transactions
Authors	C. Bayan Bruss, Anish Khazane, Jonathan Rider, Richard Serpe, Antonia Gogoglou, Keegan E. Hines
Abstract	Financial transactions can be considered edges in a heterogeneous graph between entities sending money and entities receiving money. For financial institutions, such a graph is likely large (with millions or billions of edges) while also sparsely connected. It becomes challenging to apply machine learning to such large and sparse graphs. Graph representation learning seeks to embed the nodes of a graph into a Euclidean vector space such that graph topological properties are preserved after the transformation. In this paper, we present a novel application of representation learning to bipartite graphs of credit card transactions in order to learn embeddings of account and merchant entities. Our framework is inspired by popular approaches in graph embeddings and is trained on two internal transaction datasets. This approach yields highly effective embeddings, as quantified by link prediction AUC and F1 score. Further, the resulting entity vectors retain intuitive semantic similarity that is explored through visualizations and other qualitative analyses. Finally, we show how these embeddings can be used as features in downstream machine learning business applications such as fraud detection.
Tasks	Fraud Detection, Graph Representation Learning, Link Prediction, Representation Learning, Semantic Similarity, Semantic Textual Similarity
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07225v1
PDF	https://arxiv.org/pdf/1907.07225v1.pdf
PWC	https://paperswithcode.com/paper/deeptrax-embedding-graphs-of-financial
Repo
Framework

Helen: Maliciously Secure Coopetitive Learning for Linear Models


Title	Helen: Maliciously Secure Coopetitive Learning for Linear Models
Authors	Wenting Zheng, Raluca Ada Popa, Joseph E. Gonzalez, Ion Stoica
Abstract	Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e.g., better medical research, or fraud detection). However, they often cannot share their plaintext datasets due to privacy concerns and/or business competition. In this paper, we design and build Helen, a system that allows multiple parties to train a linear model without revealing their data, a setting we call coopetitive learning. Compared to prior secure training systems, Helen protects against a much stronger adversary who is malicious and can compromise m-1 out of m parties. Our evaluation shows that Helen can achieve up to five orders of magnitude of performance improvement when compared to training using an existing state-of-the-art secure multi-party computation framework.
Tasks	Fraud Detection
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07212v2
PDF	https://arxiv.org/pdf/1907.07212v2.pdf
PWC	https://paperswithcode.com/paper/helen-maliciously-secure-coopetitive-learning
Repo
Framework

Clustering with Distributed Data


Title	Clustering with Distributed Data
Authors	Soummya Kar, Brian Swenson
Abstract	We consider $K$-means clustering in networked environments (e.g., internet of things (IoT) and sensor networks) where data is inherently distributed across nodes and processing power at each node may be limited. We consider a clustering algorithm referred to as networked $K$-means, or $NK$-means, which relies only on local neighborhood information exchange. Information exchange is limited to low-dimensional statistics and not raw data at the agents. The proposed approach develops a parametric family of multi-agent clustering objectives (parameterized by $\rho$) and associated distributed $NK$-means algorithms (also parameterized by $\rho$). The $NK$-means algorithm with parameter $\rho$ converges to a set of fixed points relative to the associated multi-agent objective (designated as `generalized minima’). By appropriate choice of $\rho$, the set of generalized minima may be brought arbitrarily close to the set of Lloyd’s minima. Thus, the $NK$-means algorithm may be used to compute Lloyd’s minima of the collective dataset up to arbitrary accuracy. \|
Tasks
Published	2019-01-01
URL	http://arxiv.org/abs/1901.00214v1
PDF	http://arxiv.org/pdf/1901.00214v1.pdf
PWC	https://paperswithcode.com/paper/clustering-with-distributed-data
Repo
Framework

Linking Graph Entities with Multiplicity and Provenance


Title	Linking Graph Entities with Multiplicity and Provenance
Authors	Jixue Liu, Selasi Kwashie, Jiuyong Li, Lin Liu, Michael Bewong
Abstract	Entity linking and resolution is a fundamental database problem with applications in data integration, data cleansing, information retrieval, knowledge fusion, and knowledge-base population. It is the task of accurately identifying multiple, differing, and possibly contradicting representations of the same real-world entity in data. In this work, we propose an entity linking and resolution system capable of linking entities across different databases and mentioned-entities extracted from text data. Our entity linking/resolution solution, called Certus, uses a graph model to represent the profiles of entities. The graph model is versatile, thus, it is capable of handling multiple values for an attribute or a relationship, as well as the provenance descriptions of the values. Provenance descriptions of a value provide the settings of the value, such as validity periods, sources, security requirements, etc. This paper presents the architecture for the entity linking system, the logical, physical, and indexing models used in the system, and the general linking process. Furthermore, we demonstrate the performance of update operations of the physical storage models when the system is implemented in two state-of-the-art database management systems, HBase and Postgres.
Tasks	Entity Linking, Information Retrieval, Knowledge Base Population
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04464v2
PDF	https://arxiv.org/pdf/1908.04464v2.pdf
PWC	https://paperswithcode.com/paper/linking-graph-entities-with-multiplicity-and
Repo
Framework

Centroid-based deep metric learning for speaker recognition


Title	Centroid-based deep metric learning for speaker recognition
Authors	Jixuan Wang, Kuan-Chieh Wang, Marc Law, Frank Rudzicz, Michael Brudno
Abstract	Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant performance gap between recognizing speakers in the training set and unseen speakers. The latter case corresponds to the few-shot learning task, where a trained model is evaluated on unseen classes. Here, we optimize a speaker embedding model with prototypical network loss (PNL), a state-of-the-art approach for the few-shot image classification task. The resulting embedding model outperforms the state-of-the-art triplet loss based models in both speaker verification and identification tasks, for both seen and unseen speakers.
Tasks	Few-Shot Image Classification, Few-Shot Learning, Image Classification, Metric Learning, Speaker Recognition, Speaker Verification
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02375v1
PDF	http://arxiv.org/pdf/1902.02375v1.pdf
PWC	https://paperswithcode.com/paper/centroid-based-deep-metric-learning-for
Repo
Framework

Fast Weakly Supervised Action Segmentation Using Mutual Consistency


Title	Fast Weakly Supervised Action Segmentation Using Mutual Consistency
Authors	Yaser Souri, Mohsen Fayyaz, Luca Minciullo, Gianpiero Francesca, Juergen Gall
Abstract	Action segmentation is the task of predicting the actions in each frame of a video. As obtaining the full annotation of videos for action segmentation is expensive, weakly supervised approaches that can learn only from transcripts are appealing. In this paper, we propose a novel, end-to-end approach for weakly supervised action segmentation based on a two-branch neural network. The two branches of our network predict two redundant but different representations for action segmentation. We propose a novel mutual consistency (MuCon) loss that enforces the consistency of the two redundant representations. Using MuCon loss together with a loss for transcript prediction, our proposed approach achieves performance statistically comparable to the state-of-the-art while being 14 times faster to train and 20 times faster during inference.
Tasks	action segmentation
Published	2019-04-05
URL	https://arxiv.org/abs/1904.03116v3
PDF	https://arxiv.org/pdf/1904.03116v3.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-action-segmentation-using
Repo
Framework

Proving Data-Poisoning Robustness in Decision Trees


Title	Proving Data-Poisoning Robustness in Decision Trees
Authors	Samuel Drews, Aws Albarghouthi, Loris D’Antoni
Abstract	Machine learning models are brittle, and small changes in the training data can result in different predictions. We study the problem of proving that a prediction is robust to data poisoning, where an attacker can inject a number of malicious elements into the training set to influence the learned model. We target decision-tree models, a popular and simple class of machine learning models that underlies many complex learning techniques. We present a sound verification technique based on abstract interpretation and implement it in a tool called Antidote. Antidote abstractly trains decision trees for an intractably large space of possible poisoned datasets. Due to the soundness of our abstraction, Antidote can produce proofs that, for a given input, the corresponding prediction would not have changed had the training set been tampered with or not. We demonstrate the effectiveness of Antidote on a number of popular datasets.
Tasks	data poisoning
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00981v1
PDF	https://arxiv.org/pdf/1912.00981v1.pdf
PWC	https://paperswithcode.com/paper/proving-data-poisoning-robustness-in-decision
Repo
Framework

Identifying through Flows for Recovering Latent Representations


Title	Identifying through Flows for Recovering Latent Representations
Authors	Shen Li, Bryan Hooi, Gim Hee Lee
Abstract	Identifiability, or recovery of the true latent representations from which the observed data originates, is de facto a fundamental goal of representation learning. Yet, most deep generative models do not address the question of identifiability, and thus fail to deliver on the promise of the recovery of the true latent sources that generate the observations. Recent work proposed identifiable generative modelling using variational autoencoders (iVAE) with a theory of identifiability. Due to the intractablity of KL divergence between variational approximate posterior and the true posterior, however, iVAE has to maximize the evidence lower bound (ELBO) of the marginal likelihood, leading to suboptimal solutions in both theory and practice. In contrast, we propose an identifiable framework for estimating latent representations using a flow-based model (iFlow). Our approach directly maximizes the marginal likelihood, allowing for theoretical guarantees on identifiability, thereby dispensing with variational approximations. We derive its optimization objective in analytical form, making it possible to train iFlow in an end-to-end manner. Simulations on synthetic data validate the correctness and effectiveness of our proposed method and demonstrate its practical advantages over other existing methods.
Tasks	Representation Learning
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12555v3
PDF	https://arxiv.org/pdf/1909.12555v3.pdf
PWC	https://paperswithcode.com/paper/identifying-through-flows-for-recovering
Repo
Framework

What do Asian Religions Have in Common? An Unsupervised Text Analytics Exploration


Title	What do Asian Religions Have in Common? An Unsupervised Text Analytics Exploration
Authors	Preeti Sah, Ernest Fokoué
Abstract	The main source of various religious teachings is their sacred texts which vary from religion to religion based on different factors like the geographical location or time of the birth of a particular religion. Despite these differences, there could be similarities between the sacred texts based on what lessons it teaches to its followers. This paper attempts to find the similarity using text mining techniques. The corpus consisting of Asian (Tao Te Ching, Buddhism, Yogasutra, Upanishad) and non-Asian (four Bible texts) is used to explore findings of similarity measures like Euclidean, Manhattan, Jaccard and Cosine on raw Document Term Frequency [DTM], normalized DTM which reveals similarity based on word usage. The performance of Supervised learning algorithms like K-Nearest Neighbor [KNN], Support Vector Machine [SVM] and Random Forest is measured based on its accuracy to predict correct scared text for any given chapter in the corpus. The K-means clustering visualizations on Euclidean distances of raw DTM reveals that there exists a pattern of similarity among these sacred texts with Upanishads and Tao Te Ching is the most similar text in the corpus.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10847v1
PDF	https://arxiv.org/pdf/1912.10847v1.pdf
PWC	https://paperswithcode.com/paper/what-do-asian-religions-have-in-common-an
Repo
Framework

Type-aware Convolutional Neural Networks for Slot Filling


Title	Type-aware Convolutional Neural Networks for Slot Filling
Authors	Heike Adel, Hinrich Schütze
Abstract	The slot filling task aims at extracting answers for queries about entities from text, such as “Who founded Apple”. In this paper, we focus on the relation classification component of a slot filling system. We propose type-aware convolutional neural networks to benefit from the mutual dependencies between entity and relation classification. In particular, we explore different ways of integrating the named entity types of the relation arguments into a neural network for relation classification, including a joint training and a structured prediction approach. To the best of our knowledge, this is the first study on type-aware neural networks for slot filling. The type-aware models lead to the best results of our slot filling pipeline. Joint training performs comparable to structured prediction. To understand the impact of the different components of the slot filling pipeline, we perform a recall analysis, a manual error analysis and several ablation studies. Such analyses are of particular importance to other slot filling researchers since the official slot filling evaluations only assess pipeline outputs. The analyses show that especially coreference resolution and our convolutional neural networks have a large positive impact on the final performance of the slot filling pipeline. The presented models, the source code of our system as well as our coreference resource is publicy available.
Tasks	Coreference Resolution, Relation Classification, Slot Filling, Structured Prediction
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00546v1
PDF	https://arxiv.org/pdf/1910.00546v1.pdf
PWC	https://paperswithcode.com/paper/type-aware-convolutional-neural-networks-for
Repo
Framework

Adversarial Training for Satire Detection: Controlling for Confounding Variables


Title	Adversarial Training for Satire Detection: Controlling for Confounding Variables
Authors	Robert McHardy, Heike Adel, Roman Klinger
Abstract	The automatic detection of satire vs. regular news is relevant for downstream applications (for instance, knowledge base population) and to improve the understanding of linguistic characteristics of satire. Recent approaches build upon corpora which have been labeled automatically based on article sources. We hypothesize that this encourages the models to learn characteristics for different publication sources (e.g., “The Onion” vs. “The Guardian”) rather than characteristics of satire, leading to poor generalization performance to unseen publication sources. We therefore propose a novel model for satire detection with an adversarial component to control for the confounding variable of publication source. On a large novel data set collected from German news (which we make available to the research community), we observe comparable satire classification performance and, as desired, a considerable drop in publication classification performance with adversarial training. Our analysis shows that the adversarial component is crucial for the model to learn to pay attention to linguistic properties of satire.
Tasks	Knowledge Base Population
Published	2019-02-28
URL	http://arxiv.org/abs/1902.11145v2
PDF	http://arxiv.org/pdf/1902.11145v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-training-for-satire-detection
Repo
Framework

Evaluating Effects of Tuition Fees: Lasso for the Case of Germany


Title	Evaluating Effects of Tuition Fees: Lasso for the Case of Germany
Authors	Konstantin Görgen, Melanie Schienle
Abstract	We study the effect of the introduction of university tuition fees on the enrollment behavior of students in Germany. For this, an appropriate Lasso-technique is crucial in order to identify the magnitude and significance of the effect due to potentially many relevant controlling factors and only a short time frame where fees existed. We show that a post-double selection strategy combined with stability selection determines a significant negative impact of fees on student enrollment and identifies relevant variables. This is in contrast to previous empirical studies and a plain linear panel regression which cannot detect any effect of tuition fees in this case. In our study, we explicitly deal with data challenges in the response variable in a transparent way and provide respective robust results. Moreover, we control for spatial cross-effects capturing the heterogeneity in the introduction scheme of fees across federal states (“Bundesl"ander”), which can set their own educational policy. We also confirm the validity of our Lasso approach in a comprehensive simulation study.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08299v1
PDF	https://arxiv.org/pdf/1909.08299v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-effects-of-tuition-fees-lasso-for
Repo
Framework

Weakly Supervised Disentanglement with Guarantees


Title	Weakly Supervised Disentanglement with Guarantees
Authors	Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole
Abstract	Learning disentangled representations that correspond to factors of variation in real-world data is critical to interpretable and human-controllable machine learning. Recently, concerns about the viability of learning disentangled representations in a purely unsupervised manner has spurred a shift toward the incorporation of weak supervision. However, there is currently no formalism that identifies when and how weak supervision will guarantee disentanglement. To address this issue, we provide a theoretical framework to assist in analyzing the disentanglement guarantees (or lack thereof) conferred by weak supervision when coupled with learning algorithms based on distribution matching. We empirically verify the guarantees and limitations of several weak supervision methods (restricted labeling, match-pairing, and rank-pairing), demonstrating the predictive power and usefulness of our theoretical framework.
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.09772v1
PDF	https://arxiv.org/pdf/1910.09772v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-disentanglement-with-1
Repo
Framework


Title	ASSED – A Framework for Identifying Physical Events through Adaptive Social Sensor Data Filtering
Authors	Abhijit Suprem, Calton Pu
Abstract	Physical event detection has long been the domain of static event processors operating on numeric sensor data. This works well for large scale strong-signal events such as hurricanes, and important classes of events such as earthquakes. However, for a variety of domains there is insufficient sensor coverage, e.g., landslides, wildfires, and flooding. Social networks have provided massive volume of data from billions of users, but data from these generic social sensors contain much more noise than physical sensors. One of the most difficult challenges presented by social sensors is \textit{concept drift}, where the terms associated with a phenomenon evolve and change over time, rendering static machine learning (ML) classifiers less effective. To address this problem, we develop the ASSED (Adaptive Social Sensor Event Detection) framework with an ML-based event processing engine and show how it can perform simple and complex physical event detection on strong- \textit{and} weak-signal with low-latency, high scalability, and accurate coverage. Specifically, ASSED is a framework to support continuous filter generation and updates with machine learning using streaming data from high-confidence sources (physical and annotated sensors) and social networks. We build ASSED to support procedures for integrating high-confidence sources into social sensor event detection to generate high-quality filters and to perform dynamic filter selection by tracking its own performance. We demonstrate ASSED capabilities through a landslide detection application that detects almost 350% more landslides compared to static approaches. More importantly, ASSED automates the handling of concept drift: four years after initial data collection and classifier training, ASSED achieves event detection accuracy of 0.988 (without expert manual intervention), compared to 0.762 for static approaches.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07596v1
PDF	https://arxiv.org/pdf/1909.07596v1.pdf
PWC	https://paperswithcode.com/paper/assed-a-framework-for-identifying-physical
Repo
Framework

Biological sex classification with structural MRI data shows increased misclassification in transgender women


Title	Biological sex classification with structural MRI data shows increased misclassification in transgender women
Authors	Claas Flint, Katharina Förster, Sophie A. Koser, Carsten Konrad, Pienie Zwitserlood, Klaus Berger, Marco Hermesdorf, Tilo Kircher, Igor Nenadic, Axel Krug, Bernhard T. Baune, Katharina Dohm, Ronny Redlich, Nils Opel, Tim Hahn, Xiaoyi Jiang, Udo Dannlowski, Dominik Grotegerd
Abstract	Transgender individuals show brain structural alterations that differ from their biological sex as well as their perceived gender. To substantiate evidence that the brain structure of transgender individuals differs from male and female, we use a combined multivariate and univariate approach. Gray matter segments resulting from voxel-based morphometry preprocessing of N = 1753 cisgender (CG) healthy participants were used to train (N = 1402) and validate (20% hold-out N = 351) a support vector machine classifying the biological sex. As a second validation, we classified N = 1104 patients with depression. A third validation was performed using the matched CG sample of the transgender women (TW) application sample. Subsequently, the classifier was applied to N = 25 TW. Finally, we compared brain volumes of CG-men, women and TW pre/post treatment (CHT) in a univariate analysis controlling for sexual orientation, age and total brain volume. The application of our biological sex classifier to the transgender sample resulted in a significantly lower true positive rate (TPR-male = 56.0%). The TPR did not differ between CG-individuals with (TPR-male = 86.9%) and without depression (TPR-male = 88.5%). The univariate analysis of the transgender application sample revealed that TW pre/post treatment show brain structural differences from CG-women and CG-men in the putamen and insula, as well as the whole-brain analysis. Our results support the hypothesis that brain structure in TW differs from brain structure of their biological sex (male) as well as their perceived gender (female). This finding substantiates evidence that transgender individuals show specific brain structural alterations leading to a different pattern of brain structure than CG individuals.
Tasks
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10617v1
PDF	https://arxiv.org/pdf/1911.10617v1.pdf
PWC	https://paperswithcode.com/paper/biological-sex-classification-with-structural
Repo
Framework