Ori Katz

Oren Barkan, Edan Hauon, Avi Caciularu et al.

Transformer-based language models significantly advanced the state-of-the-art in many linguistic tasks. As this revolution continues, the ability to explain model predictions has become a major area of interest for the NLP community. In this work, we present Gradient Self-Attention Maps (Grad-SAM) - a novel gradient-based method that analyzes self-attention units and identifies the input elements that explain the model's prediction the best. Extensive evaluations on various benchmarks show that Grad-SAM obtains significant improvements over state-of-the-art alternatives.

Oren Barkan, Avi Caciularu, Idan Rejwan et al.

We present Variational Bayesian Network (VBN) - a novel Bayesian entity representation learning model that utilizes hierarchical and relational side information and is particularly useful for modeling entities in the ``long-tail'', where the data is scarce. VBN provides better modeling for long-tail entities via two complementary mechanisms: First, VBN employs informative hierarchical priors that enable information propagation between entities sharing common ancestors. Additionally, VBN models explicit relations between entities that enforce complementary structure and consistency, guiding the learned representations towards a more meaningful arrangement in space. Second, VBN represents entities by densities (rather than vectors), hence modeling uncertainty that plays a complementary role in coping with data scarcity. Finally, we propose a scalable Variational Bayes optimization algorithm that enables fast approximate Bayesian inference. We evaluate the effectiveness of VBN on linguistic, recommendations, and medical inference tasks. Our findings show that VBN outperforms other existing methods across multiple datasets, and especially in the long-tail.

Oren Barkan, Tal Reiss, Jonathan Weill et al.

Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although being a highly addressed problem, the evaluation of proposed methods for VSD is often based on a proxy of an identification-retrieval task, evaluating the ability of a model to retrieve different images of the same object. We posit that evaluating VSD methods based on identification tasks is limited, and faithful evaluation must rely on expert annotations. In this paper, we introduce the first large-scale fashion visual similarity benchmark dataset, consisting of more than 110K expert-annotated image pairs. Besides this major contribution, we share insight from the challenges we faced while curating this dataset. Based on these insights, we propose a novel and efficient labeling procedure that can be applied to any dataset. Our analysis examines its limitations and inductive biases, and based on these findings, we propose metrics to mitigate those limitations. Though our primary focus lies on visual similarity, the methodologies we present have broader applications for discovering and evaluating perceptual similarity across various domains.

Oren Barkan, Noam Razin, Itzik Malkiel et al.

Recent state-of-the-art natural language understanding models, such as BERT and XLNet, score a pair of sentences (A and B) using multiple cross-attention operations - a process in which each word in sentence A attends to all words in sentence B and vice versa. As a result, computing the similarity between a query sentence and a set of candidate sentences, requires the propagation of all query-candidate sentence-pairs throughout a stack of cross-attention layers. This exhaustive process becomes computationally prohibitive when the number of candidate sentences is large. In contrast, sentence embedding techniques learn a sentence-to-vector mapping and compute the similarity between the sentence vectors via simple elementary operations. In this paper, we introduce Distilled Sentence Embedding (DSE) - a model that is based on knowledge distillation from cross-attentive models, focusing on sentence-pair tasks. The outline of DSE is as follows: Given a cross-attentive teacher model (e.g. a fine-tuned BERT), we train a sentence embedding based student model to reconstruct the sentence-pair scores obtained by the teacher model. We empirically demonstrate the effectiveness of DSE on five GLUE sentence-pair tasks. DSE significantly outperforms several ELMO variants and other sentence embedding methods, while accelerating computation of the query-candidate sentence-pairs similarities by several orders of magnitude, with an average relative degradation of 4.6% compared to BERT. Furthermore, we show that DSE produces sentence embeddings that reach state-of-the-art performance on universal sentence representation benchmarks. Our code is made publicly available at https://github.com/microsoft/Distilled-Sentence-Embedding.

Oren Barkan, Roy Hirsch, Ori Katz et al.

A major challenge in collaborative filtering methods is how to produce recommendations for cold items (items with no ratings), or integrate cold item into an existing catalog. Over the years, a variety of hybrid recommendation models have been proposed to address this problem by utilizing items' metadata and content along with their ratings or usage patterns. In this work, we wish to revisit the cold start problem in order to draw attention to an overlooked challenge: the ability to integrate and balance between (regular) warm items and completely cold items. In this case, two different challenges arise: (1) preserving high quality performance on warm items, while (2) learning to promote cold items to relevant users. First, we show that these two objectives are in fact conflicting, and the balance between them depends on the business needs and the application at hand. Next, we propose a novel hybrid recommendation algorithm that bridges these two conflicting objectives and enables a harmonized balance between preserving high accuracy for warm items while effectively promoting completely cold items. We demonstrate the effectiveness of the proposed algorithm on movies, apps, and articles recommendations, and provide an empirical analysis of the cold-warm trade-off.

Uri Shaham, Jonathan Svirsky, Ori Katz et al.

Latent variable discovery is a central problem in data analysis with a broad range of applications in applied science. In this work, we consider data given as an invertible mixture of two statistically independent components and assume that one of the components is observed while the other is hidden. Our goal is to recover the hidden component. For this purpose, we propose an autoencoder equipped with a discriminator. Unlike the standard nonlinear ICA problem, which was shown to be non-identifiable, in the special case of ICA we consider here, we show that our approach can recover the component of interest up to entropy-preserving transformation. We demonstrate the performance of the proposed approach in several tasks, including image synthesis, voice cloning, and fetal ECG extraction.

Oren Barkan, Omri Armstrong, Amir Hertz et al.

We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activation information from multiple network layers, GAM offers improved visual explanations, when compared to existing alternatives. The algorithmic advantages of GAM are explained in detail, and validated empirically, where it is shown that GAM outperforms its alternatives across various tasks and datasets.

Itzik Malkiel, Oren Barkan, Avi Caciularu et al.

Language models that utilize extensive self-supervised pre-training from unlabeled text, have recently shown to significantly advance the state-of-the-art performance in a variety of language understanding tasks. However, it is yet unclear if and how these recent models can be harnessed for conducting text-based recommendations. In this work, we introduce RecoBERT, a BERT-based approach for learning catalog-specialized language models for text-based item recommendations. We suggest novel training and inference procedures for scoring similarities between pairs of items, that don't require item similarity labels. Both the training and the inference techniques were designed to utilize the unlabeled structure of textual catalogs, and minimize the discrepancy between them. By incorporating four scores during inference, RecoBERT can infer text-based item-to-item similarities more accurately than other techniques. In addition, we introduce a new language understanding task for wine recommendations using similarities based on professional wine reviews. As an additional contribution, we publish annotated recommendations dataset crafted by human wine experts. Finally, we evaluate RecoBERT and compare it to various state-of-the-art NLP models on wine and fashion recommendations tasks.

Ori Katz, Roy R. Lederman, Ronen Talmon

In this paper, we consider data acquired by multimodal sensors capturing complementary aspects and features of a measured phenomenon. We focus on a scenario in which the measurements share mutual sources of variability but might also be contaminated by other measurement-specific sources such as interferences or noise. Our approach combines manifold learning, which is a class of nonlinear data-driven dimension reduction methods, with the well-known Riemannian geometry of symmetric and positive-definite (SPD) matrices. Manifold learning typically includes the spectral analysis of a kernel built from the measurements. Here, we take a different approach, utilizing the Riemannian geometry of the kernels. In particular, we study the way the spectrum of the kernels changes along geodesic paths on the manifold of SPD matrices. We show that this change enables us, in a purely unsupervised manner, to derive a compact, yet informative, description of the relations between the measurements, in terms of their underlying components. Based on this result, we present new algorithms for extracting the common latent components and for identifying common and measurement-specific components.

Tomer Yeminy, Ori Katz

Optical imaging through scattering media is a fundamental challenge in many applications. Recently, substantial breakthroughs such as imaging through biological tissues and looking around corners have been obtained by the use of wavefront-shaping approaches. However, these require an implanted guide-star for determining the wavefront correction, controlled coherent illumination, and most often raster scanning of the shaped focus. Alternative novel computational approaches that exploit speckle correlations, avoid guide-stars and wavefront control but are limited to small two-dimensional objects contained within the memory-effect correlations range. Here, we present a new concept, image-guided wavefront-shaping, allowing non-invasive, guidestar-free, widefield, incoherent imaging through highly scattering layers, without illumination control. Most importantly, the wavefront-correction is found even for objects that are larger than the memory-effect range, by blindly optimizing image-quality metrics. We demonstrate imaging of extended objects through highly-scattering layers and multi-core fibers, paving the way for non-invasive imaging in various applications, from microscopy to endoscopy.

Oren Barkan, Ori Katz, Noam Koenigstein

An important problem in multiview representation learning is finding the optimal combination of views with respect to the specific task at hand. To this end, we introduce NAM: a Neural Attentive Multiview machine that learns multiview item representations and similarity by employing a novel attention mechanism. NAM harnesses multiple information sources and automatically quantifies their relevancy with respect to a supervised task. Finally, a very practical advantage of NAM is its robustness to the case of dataset with missing views. We demonstrate the effectiveness of NAM for the task of movies and app recommendations. Our evaluations indicate that NAM outperforms single view models as well as alternative multiview methods on item recommendations tasks, including cold-start scenarios.

Oren Barkan, Avi Caciularu, Ori Katz et al.

Factorization methods for recommender systems tend to represent users as a single latent vector. However, user behavior and interests may change in the context of the recommendations that are presented to the user. For example, in the case of movie recommendations, it is usually true that earlier user data is less informative than more recent data. However, it is possible that a certain early movie may become suddenly more relevant in the presence of a popular sequel movie. This is just a single example of a variety of possible dynamically altering user interests in the presence of a potential new recommendation. In this work, we present Attentive Item2vec (AI2V) - a novel attentive version of Item2vec (I2V). AI2V employs a context-target attention mechanism in order to learn and capture different characteristics of user historical behavior (context) with respect to a potential recommended item (target). The attentive context-target mechanism enables a final neural attentive user representation. We demonstrate the effectiveness of AI2V on several datasets, where it is shown to outperform other baselines.

Oren Barkan, David Tsiris, Ori Katz et al.

Sound synthesis is a complex field that requires domain expertise. Manual tuning of synthesizer parameters to match a specific sound can be an exhaustive task, even for experienced sound engineers. In this paper, we introduce InverSynth - an automatic method for synthesizer parameters tuning to match a given input sound. InverSynth is based on strided convolutional neural networks and is capable of inferring the synthesizer parameters configuration from the input spectrogram and even from the raw audio. The effectiveness InverSynth is demonstrated on a subtractive synthesizer with four frequency modulated oscillators, envelope generator and a gater effect. We present extensive quantitative and qualitative results that showcase the superiority InverSynth over several baselines. Furthermore, we show that the network depth is an important factor that contributes to the prediction accuracy.

Ori Katz, Ronen Talmon, Yu-Lun Lo et al.

The problem of information fusion from multiple data-sets acquired by multimodal sensors has drawn significant research attention over the years. In this paper, we focus on a particular problem setting consisting of a physical phenomenon or a system of interest observed by multiple sensors. We assume that all sensors measure some aspects of the system of interest with additional sensor-specific and irrelevant components. Our goal is to recover the variables relevant to the observed system and to filter out the nuisance effects of the sensor-specific variables. We propose an approach based on manifold learning, which is particularly suitable for problems with multiple modalities, since it aims to capture the intrinsic structure of the data and relies on minimal prior model knowledge. Specifically, we propose a nonlinear filtering scheme, which extracts the hidden sources of variability captured by two or more sensors, that are independent of the sensor-specific components. In addition to presenting a theoretical analysis, we demonstrate our technique on real measured data for the purpose of sleep stage assessment based on multiple, multimodal sensor measurements. We show that without prior knowledge on the different modalities and on the measured system, our method gives rise to a data-driven representation that is well correlated with the underlying sleep process and is robust to noise and sensor-specific effects.

Oren Barkan, Noam Koenigstein, Eylon Yogev et al.

In Recommender Systems research, algorithms are often characterized as either Collaborative Filtering (CF) or Content Based (CB). CF algorithms are trained using a dataset of user preferences while CB algorithms are typically based on item profiles. These approaches harness different data sources and therefore the resulting recommended items are generally very different. This paper presents the CB2CF, a deep neural multiview model that serves as a bridge from items content into their CF representations. CB2CF is a real-world algorithm designed for Microsoft Store services that handle around a billion users worldwide. CB2CF is demonstrated on movies and apps recommendations, where it is shown to outperform an alternative CB model on completely cold items.