Search Results for author: Kira Radinsky

Found 21 papers, 16 papers with code

Interpretable Multivariate Time Series Forecasting Using Neural Fourier Transform

1 code implementation22 May 2024 Noam Koren, Kira Radinsky

Multivariate time series forecasting is a pivotal task in several domains, including financial planning, medical diagnostics, and climate science.

Multivariate Time Series Forecasting Time Series

Leveraging World Events to Predict E-Commerce Consumer Demand under Anomaly

1 code implementation22 May 2024 Dan Kalifa, Uriel Singer, Ido Guy, Guy D. Rosin, Kira Radinsky

However, reliable time series sales forecasting for e-commerce is difficult, especially during periods with many anomalies, as can often happen during pandemics, abnormal weather, or sports events.

Time Series

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information

no code implementations14 Mar 2024 Shadi Iskander, Kira Radinsky, Yonatan Belinkov

Mitigating social biases typically requires identifying the social groups associated with each data sample.

Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection

1 code implementation17 May 2023 Shadi Iskander, Kira Radinsky, Yonatan Belinkov

In this work, we propose Iterative Gradient-Based Projection (IGBP), a novel method for removing non-linear encoded concepts from neural representations.

Attribute

tBDFS: Temporal Graph Neural Network Leveraging DFS

1 code implementation12 Jun 2022 Uriel Singer, Haggai Roitman, Ido Guy, Kira Radinsky

A common approach employed by most previous works is to apply a layer that aggregates information from the historical neighbors of a node.

Graph Neural Network Link Prediction

What If: Generating Code to Answer Simulation Questions

1 code implementation16 Apr 2022 Gal Peretz, Kira Radinsky

The dataset is composed of process texts, simulation questions, and their corresponding computer codes represented by the DSL. We propose a neural program synthesis approach based on reinforcement learning with a novel state-transition semantic reward.

Program Synthesis Semantic Similarity +1

Temporal Attention for Language Models

1 code implementation Findings (NAACL) 2022 Guy D. Rosin, Kira Radinsky

We leverage these representations for the task of semantic change detection; we apply our proposed mechanism to BERT and experiment on three datasets in different languages (English, German, and Latin) that also vary in time, size, and genre.

Change Detection

EqGNN: Equalized Node Opportunity in Graphs

1 code implementation19 Aug 2021 Uriel Singer, Kira Radinsky

To the best of our knowledge, we are the first to optimize GNNs for the equalized odds criteria.

Attribute Fairness

Event-Driven Query Expansion

1 code implementation22 Dec 2020 Guy D. Rosin, Ido Guy, Kira Radinsky

A significant number of event-related queries are issued in Web search.

Ad-Hoc Information Retrieval Retrieval

Generating Timelines by Modeling Semantic Change

1 code implementation CONLL 2019 Guy D. Rosin, Kira Radinsky

Though languages can evolve slowly, they can also react strongly to dramatic world events.

Word Embeddings

Explorations and Lessons Learned in Building an Autonomous Formula SAE Car from Simulations

4 code implementations15 May 2019 Dean Zadok, Tom Hirshberg, Amir Biran, Kira Radinsky, Ashish Kapoor

This paper describes the exploration and learnings during the process of developing a self-driving algorithm in simulation, followed by deployment on a real car.

Robotics

Node Embedding over Temporal Graphs

1 code implementation21 Mar 2019 Uriel Singer, Ido Guy, Kira Radinsky

In this work, we present a method for node embedding in temporal graphs.

Clustering Link Prediction +1

Latent Entities Extraction: How to Extract Entities that Do Not Appear in the Text?

1 code implementation CONLL 2018 Eylon Shoshan, Kira Radinsky

The dataset contains text descriptions of biological processes, and for each process, all of the involved entities in the process are labeled, including implicitly mentioned ones.

Multi-Task Learning named-entity-recognition +4

Learning to Focus when Ranking Answers

no code implementations8 Aug 2018 Dana Sagi, Tzoof Avny, Kira Radinsky, Eugene Agichtein

One of the main challenges in ranking is embedding the query and document pairs into a joint feature space, which can then be fed to a learning-to-rank algorithm.

Feature Engineering Learning-To-Rank +1

Accelerating Prototype-Based Drug Discovery using Conditional Diversity Networks

2 code implementations8 Apr 2018 Shahar Harel, Kira Radinsky

In this work, we develop an algorithmic unsupervised-approach that automatically generates potential drug molecules given a prototype drug.

Diversity Drug Discovery +1

Learning Word Relatedness over Time

1 code implementation EMNLP 2017 Guy D. Rosin, Eytan Adar, Kira Radinsky

Search systems are often focused on providing relevant results for the "now", assuming both corpora and user needs that focus on the present.

Learning to Predict from Textual Data

no code implementations4 Feb 2014 Kira Radinsky, Sagie Davidovich, Shaul Markovitch

Our Pundit algorithm generalizes examples of causality pairs to infer a causality predictor.

Language Modelling World Knowledge

Cannot find the paper you are looking for? You can Submit a new open access paper.