no code implementations • 15 Mar 2023 • Fartash Faghri, Hadi Pouransari, Sachin Mehta, Mehrdad Farajtabar, Ali Farhadi, Mohammad Rastegari, Oncel Tuzel
Models pretrained on ImageNet+ and fine-tuned on CIFAR-100+, Flowers-102+, and Food-101+, reach up to 3. 4% improved accuracy.
no code implementations • 5 Jul 2022 • Caglar Gulcehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Mehrdad Farajtabar, Matt Hoffman, Razvan Pascanu, Arnaud Doucet
Also, we empirically identify three phases of learning that explain the impact of implicit regularization on the learning dynamics and found that bootstrapping alone is insufficient to explain the collapse of the effective rank.
no code implementations • 20 Feb 2022 • Thang Doan, Seyed Iman Mirzadeh, Mehrdad Farajtabar
A growing body of research in continual learning focuses on the catastrophic forgetting problem.
no code implementations • 1 Feb 2022 • Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
However, in this work, we show that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones.
no code implementations • 21 Oct 2021 • Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Huiyi Hu, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts.
no code implementations • ICML Workshop INNF 2021 • Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu
Learning new tasks continuously without forgetting on a constantly changing data distribution is essential for real-world problems but extremely challenging for modern deep learning.
no code implementations • 23 Nov 2020 • Mehrdad Farajtabar, Andrew Lee, Yuanjian Feng, Vishal Gupta, Peter Dolan, Harish Chandran, Martin Szummer
Estimating individual and average treatment effects from observational data is an important problem in many domains such as healthcare and e-commerce.
1 code implementation • ICLR 2021 • Seyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur, Razvan Pascanu, Hassan Ghasemzadeh
Continual (sequential) training and multitask (simultaneous) training are often attempting to solve the same overall objective: to find a solution that performs well on all considered tasks.
no code implementations • 6 Oct 2020 • Yogesh Balaji, Mehrdad Farajtabar, Dong Yin, Alex Mott, Ang Li
However, a degraded performance is observed for ER with small memory.
no code implementations • 19 Jun 2020 • Dong Yin, Mehrdad Farajtabar, Ang Li, Nir Levine, Alex Mott
This problem is often referred to as catastrophic forgetting, a key challenge in continual learning of neural networks.
no code implementations • NeurIPS 2020 • Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine, Dilan Gorur, Chris Harris, Dale Schuurmans
This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs).
4 code implementations • NeurIPS 2020 • Seyed Iman Mirzadeh, Mehrdad Farajtabar, Razvan Pascanu, Hassan Ghasemzadeh
However, there has been limited prior work extensively analyzing the impact that different training regimes -- learning rate, batch size, regularization method-- can have on forgetting.
2 code implementations • NeurIPS 2020 • Jiachen Yang, Ang Li, Mehrdad Farajtabar, Peter Sunehag, Edward Hughes, Hongyuan Zha
The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years.
2 code implementations • 24 Apr 2020 • Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Hassan Ghasemzadeh
However, it is more reliable to preserve the knowledge it has learned from the previous tasks.
no code implementations • NeurIPS 2020 • Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett
Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another.
no code implementations • 15 Oct 2019 • Mehrdad Farajtabar, Navid Azizan, Alex Mott, Ang Li
In this paper, we propose to address this issue from a parameter space perspective and study an approach to restrict the direction of the gradient updates to avoid forgetting previously-learned data.
1 code implementation • ICCV 2019 • Ang Li, Huiyi Hu, Piotr Mirowski, Mehrdad Farajtabar
The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL).
1 code implementation • ICLR 2019 • Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha
We present DyRep - a novel modeling framework for dynamic graphs that posits representation learning as a latent mediation process bridging two observed processes namely -- dynamics of the network (realized as topological evolution) and dynamics on the network (realized as activities between nodes).
3 code implementations • 9 Feb 2019 • Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Ang Li, Nir Levine, Akihiro Matsukawa, Hassan Ghasemzadeh
To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher.
1 code implementation • 5 Dec 2018 • Yunshu Du, Wojciech M. Czarnecki, Siddhant M. Jayakumar, Mehrdad Farajtabar, Razvan Pascanu, Balaji Lakshminarayanan
One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations.
no code implementations • 11 Mar 2018 • Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha
How can we effectively encode evolving information over dynamic graphs into low-dimensional representations?
no code implementations • ICML 2018 • Mehrdad Farajtabar, Yin-Lam Chow, Mohammad Ghavamzadeh
In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time.
no code implementations • 12 Dec 2017 • Amrita Gupta, Mehrdad Farajtabar, Bistra Dilkina, Hongyuan Zha
The spread of invasive species to new areas threatens the stability of ecosystems and causes major economic losses in agriculture and forestry.
1 code implementation • NeurIPS 2017 • Shuai Xiao, Mehrdad Farajtabar, Xiaojing Ye, Junchi Yan, Le Song, Hongyuan Zha
Point processes are becoming very popular in modeling asynchronous sequential data due to their sound mathematical foundation and strength in modeling a variety of real-world phenomena.
no code implementations • 24 Mar 2017 • Shuai Xiao, Junchi Yan, Mehrdad Farajtabar, Le Song, Xiaokang Yang, Hongyuan Zha
A variety of real-world processes (over networks) produce sequences of data whose complex temporal dynamics need to be studied.
no code implementations • ICML 2017 • Mehrdad Farajtabar, Jiachen Yang, Xiaojing Ye, Huan Xu, Rakshit Trivedi, Elias Khalil, Shuang Li, Le Song, Hongyuan Zha
We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model.
1 code implementation • 4 Mar 2017 • Seyed Abbas Hosseini, Keivan Alizadeh, Ali Khodadadi, Ali Arabzadeh, Mehrdad Farajtabar, Hongyuan Zha, Hamid R. Rabiee
Poisson factorization is a probabilistic model of users and items for recommendation systems, where the so-called implicit consumer data is modeled by a factorized Poisson distribution.
no code implementations • 24 Oct 2016 • Behzad Tabibian, Isabel Valera, Mehrdad Farajtabar, Le Song, Bernhard Schölkopf, Manuel Gomez-Rodriguez
Then, we propose a temporal point process modeling framework that links these temporal traces to robust, unbiased and interpretable notions of information reliability and source trustworthiness.
no code implementations • 22 May 2016 • Mohammad Reza Karimi, Erfan Tavakoli, Mehrdad Farajtabar, Le Song, Manuel Gomez-Rodriguez
Many users in online social networks are constantly trying to gain attention from their followers by broadcasting posts to them.
no code implementations • 29 Mar 2016 • Shuang Li, Yao Xie, Mehrdad Farajtabar, Apurv Verma, Le Song
Large volume of networked streaming event data are becoming increasingly available in a wide variety of applications, such as social network analysis, Internet traffic monitoring and healthcare analytics.
no code implementations • 14 Feb 2016 • Hongteng Xu, Mehrdad Farajtabar, Hongyuan Zha
In this paper, we propose an effective method, learning Granger causality, for a special but significant type of point processes --- Hawkes process.
no code implementations • 13 Nov 2015 • Mehrdad Farajtabar, Safoora Yousefi, Long Q. Tran, Le Song, Hongyuan Zha
In our experiments, we demonstrate that our algorithm is able to achieve the-state-of-the-art performance in terms of analyzing, predicting, and prioritizing events.
1 code implementation • NeurIPS 2015 • Mehrdad Farajtabar, Yichen Wang, Manuel Gomez Rodriguez, Shuang Li, Hongyuan Zha, Le Song
Information diffusion in online social networks is affected by the underlying network topology, but it also has the power to change it.
no code implementations • NeurIPS 2014 • Mehrdad Farajtabar, Nan Du, Manuel Gomez Rodriguez, Isabel Valera, Hongyuan Zha, Le Song
Events in an online social network can be categorized roughly into endogenous events, where users just respond to the actions of their neighbors within the network, or exogenous events, where users take actions due to drives external to the network.
no code implementations • CVPR 2013 • Amirreza Shaban, Hamid R. Rabiee, Mehrdad Farajtabar, Marjan Ghazvininejad
Exploiting the local similarity of a descriptor and its nearby bases, a global measure of association of a descriptor to all the bases is computed.