activity
20162026
most citedGrad-SAM: Explaining Transformers via Gradient Self-Attention Maps

43 citations · 49 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2024

BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation

Oren Barkan, Yehonatan Elisha, Jonathan Weill +1

Two prominent challenges in explainability research involve 1) the nuanced evaluation of explanations and 2) the modeling of missing information through baseline representations. T…

cs.LG2023

Representation Learning via Variational Bayesian Networks

Oren Barkan, Avi Caciularu, Idan Rejwan +4

We present Variational Bayesian Network (VBN) - a novel Bayesian entity representation learning model that utilizes hierarchical and relational side information and is particularly…

cs.LG202243 cited

Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps

Oren Barkan, Edan Hauon, Avi Caciularu +4

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 b…

cs.LG2020

Neural Attentive Multiview Machines

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 Ne…

cs.LG20191 cited

Multiscale Self Attentive Convolutions for Vision and Language Modeling

Oren Barkan

Self attention mechanisms have become a key building block in many state-of-the-art language understanding models. In this paper, we show that the self attention operator can be fo…

cs.LG2019

Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding

Oren Barkan, Noam Razin, Itzik Malkiel +3

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…