Publications

Staged independent learning: Towards decentralized cooperative multi-agent Reinforcement Learning
Hadi Nekoei
Akilesh Badrinaaraayanan
Amit Sinha
Mohammad Amini
Janarthanan Rajendran
Aditya Mahajan
Sarath Chandar
We empirically show that classic ideas from two-time scale stochastic approximation \citep{borkar1997stochastic} can be combined with sequen… (see more)tial iterative best response (SIBR) to solve complex cooperative multi-agent reinforcement learning (MARL) problems. We first start with giving a multi-agent estimation problem as a motivating example where SIBR converges while parallel iterative best response (PIBR) does not. Then we present a general implementation of staged multi-agent RL algorithms based on SIBR and multi-time scale stochastic approximation, and show that our new methods which we call Staged Independent Proximal Policy Optimization (SIPPO) and Staged Independent Q-learning (SIQL) outperform state-of-the-art independent learning on almost all the tasks in the epymarl \citep{papoudakis2020benchmarking} benchmark. This can be seen as a first step towards more decentralized MARL methods based on SIBR and multi-time scale learning.
2022-04-25
ICLR.cc/2022/Workshop/GMS (published)
openreview.net
openreview.net
VisPaD: Visualization and Pattern Discovery for Fighting Human Trafficking
Pratheeksha Nair
Yifei Li
Catalina Vajiac
Andreas Olligschlaeger
Meng-Chieh Lee
Namyong Park
Duen Horng Chau
Christos Faloutsos
Reihaneh Rabbany
Chieh Lee
2022-04-25
The Web Conference (published)
doi.org
VisPaD: Visualization and Pattern Discovery for Fighting Human Trafficking
Pratheeksha Nair
Yifei Li
Catalina Vajiac
Andreas Olligschlaeger
Meng-Chieh Lee
Namyong Park
Duen Horng Chau
Christos Faloutsos
Reihaneh Rabbany
Chieh Lee
Human trafficking analysts investigate groups of related online escort advertisements (called micro-clusters) to detect suspicious activitie… (see more)s and identify various modus operandi. This task is complex as it requires finding patterns and linked meta-data across micro-clusters such as the geographical spread of ads, cluster sizes, etc. Additionally, drawing insights from the data is challenging without visualizing these micro-clusters. To address this, in close-collaboration with domain experts, we built VisPaD, a novel interactive way for characterizing and visualizing micro-clusters and their associated meta-data, all in one place. VisPaD helps discover underlying patterns in the data by projecting micro-clusters in a lower dimensional space. It also allows the user to select micro-clusters involved in suspicious patterns and interactively examine them leading to faster detection and identification of trends in the data. A demo of VisPaD is also released1.
2022-04-25
The Web Conference (published)
doi.org
Local Learning with Neuron Groups
Adeetya Patel
Michael Eickenberg
Eugene Belilovsky
2022-04-21
ICLR.cc/2022/Workshop/Cells2Societies (poster)
doi.org
openreview.net
Summarizing Societies: Agent Abstraction in Multi-Agent Reinforcement Learning
Amin Memarian
Maximilian Puelma Touzel
Matthew D Riemer
Rupali Bhati
Irina Rish
Agents cannot make sense of many-agent societies through direct consideration of small-scale, low-level agent identities, but instead must r… (see more)ecognize emergent collective identities. Here, we take a first step towards a framework for recognizing this structure in large groups of low-level agents so that they can be modeled as a much smaller number of high-level agents—a process that we call agent abstraction. We illustrate this process by extending bisimulation metrics for state abstraction in reinforcement learning to the setting of multi-agent reinforcement learning and analyze a straightforward, if crude, abstraction based on experienced joint actions. It addresses non-stationarity due to other learning agents by improving minimax regret by a intuitive factor. To test if this compression factor provides signal for higher-level agency, we applied it to a large dataset of human play of the popular social dilemma game Diplomacy. We find that it correlates strongly with the degree of ground-truth abstraction of low-level units into the human players.
2022-04-21
ICLR.cc/2022/Workshop/Cells2Societies (poster)
openreview.net
openreview.net
A Strong Node Classification Baseline for Temporal Graphs
Farimah Poursafaei
Željko Žilić
Reihaneh Rabbany
2022-04-20
Proceedings of the 2022 SIAM International Conference on Data Mining (SDM) (published)
doi.org
Microscopy-BIDS: An Extension to the Brain Imaging Data Structure for Microscopy Data
Marie-Hélène Bourget
L. Kamentsky
Satrajit S. Ghosh
Giacomo Mazzamuto
Alberto Lazari
Christopher J. Markiewicz
Robert Oostenveld
Guiomar Niso
Yaroslav O. Halchenko
Ilona Lipp
Sylvain Takerkart
P. Toussaint
Ali Raza Khan
Gustav Nilsonne
Filippo Maria Castelli
Julien Cohen-Adad
The Brain Imaging Data Structure (BIDS) is a specification for organizing, sharing, and archiving neuroimaging data and metadata in a reusab… (see more)le way. First developed for magnetic resonance imaging (MRI) datasets, the community-led specification evolved rapidly to include other modalities such as magnetoencephalography, positron emission tomography, and quantitative MRI (qMRI). In this work, we present an extension to BIDS for microscopy imaging data, along with example datasets. Microscopy-BIDS supports common imaging methods, including 2D/3D, ex/in vivo, micro-CT, and optical and electron microscopy. Microscopy-BIDS also includes comprehensible metadata definitions for hardware, image acquisition, and sample properties. This extension will facilitate future harmonization efforts in the context of multi-modal, multi-scale imaging such as the characterization of tissue microstructure with qMRI.
2022-04-19
Frontiers in Neuroscience (published)
doi.org
Microscopy-BIDS: An Extension to the Brain Imaging Data Structure for Microscopy Data
Marie-Hélène Bourget
Lee Kamentsky
Satrajit S. Ghosh
Giacomo Mazzamuto
Alberto Lazari
Christopher J. Markiewicz
Robert Oostenveld
Guiomar Niso
Yaroslav O. Halchenko
Ilona Lipp
Sylvain Takerkart
Paule-Joanne Toussaint
Ali R. Khan
Gustav Nilsonne
Filippo Maria Castelli
Stefan Ross Eric Franklin Anthony Rémi Christopher J. Taylor Appelhoff
Julien Cohen-Adad
The Brain Imaging Data Structure (BIDS) is a specification for organizing, sharing, and archiving neuroimaging data and metadata in a reusab… (see more)le way. First developed for magnetic resonance imaging (MRI) datasets, the community-led specification evolved rapidly to include other modalities such as magnetoencephalography, positron emission tomography, and quantitative MRI (qMRI). In this work, we present an extension to BIDS for microscopy imaging data, along with example datasets. Microscopy-BIDS supports common imaging methods, including 2D/3D, ex/in vivo, micro-CT, and optical and electron microscopy. Microscopy-BIDS also includes comprehensible metadata definitions for hardware, image acquisition, and sample properties. This extension will facilitate future harmonization efforts in the context of multi-modal, multi-scale imaging such as the characterization of tissue microstructure with qMRI.
2022-04-19
Frontiers in Neuroscience (published)
doi.org
On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
Nouha Dziri
Sivan Milton
Mo Yu
Osmar R Zaiane
Siva Reddy
Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallu… (see more)cination. In this work, we investigate the underlying causes of this phenomenon: is hallucination due to the training data, or to the models? We conduct a comprehensive human study on both existing knowledge-grounded conversational benchmarks and several state-of-the-art models. Our study reveals that the standard benchmarks consist of > 60% hallucinated responses, leading to models that not only hallucinate but even amplify hallucinations. Our findings raise important questions on the quality of existing datasets and models trained using them. We make our annotations publicly available for future research.
2022-04-17
ArXiv (preprint)
doi.org
arxiv.org
On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
Nouha Dziri
Sivan Milton
Mo Yu
Osmar R Zaiane
Siva Reddy
Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallu… (see more)cination. In this work, we investigate the underlying causes of this phenomenon: is hallucination due to the training data, or to the models? We conduct a comprehensive human study on both existing knowledge-grounded conversational benchmarks and several state-of-the-art models. Our study reveals that the standard benchmarks consist of > 60% hallucinated responses, leading to models that not only hallucinate but even amplify hallucinations. Our findings raise important questions on the quality of existing datasets and models trained using them. We make our annotations publicly available for future research.
2022-04-17
ArXiv (preprint)
doi.org
arxiv.org
Improving Passage Retrieval with Zero-Shot Question Generation
Devendra Singh Sachan
Mike Lewis
Mandar S. Joshi
Armen Aghajanyan
Wen-292 Tau Yih
Joelle Pineau
Luke Zettlemoyer
We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retr… (see more)ieved passages with a zero-shot question generation model, which uses a pre-trained language model to compute the probability of the input question conditioned on a retrieved passage. This approach can be applied on top of any retrieval method (e.g. neural or keyword-based), does not require any domain- or task-specific training (and therefore is expected to generalize better to data distribution shifts), and provides rich cross-attention between query and passage (i.e. it must explain every token in the question). When evaluated on a number of open-domain retrieval datasets, our re-ranker improves strong unsupervised retrieval models by 6%-18% absolute and strong supervised models by up to 12% in terms of top-20 passage retrieval accuracy. We also obtain new state-of-the-art results on full open-domain question answering by simply adding the new re-ranker to existing models with no further changes.
2022-04-15
ArXiv (preprint)
doi.org
arxiv.org
Evolution of cell size control is canalized towards adders or sizers by cell cycle structure and selective pressures
Felix Proulx-Giraldeau
J. Skotheim
Paul François
Cell size is controlled to be within a specific range to support physiological function. To control their size, cells use diverse mechanisms… (see more) ranging from ‘sizers’, in which differences in cell size are compensated for in a single cell division cycle, to ‘adders’, in which a constant amount of cell growth occurs in each cell cycle. This diversity raises the question why a particular cell would implement one rather than another mechanism? To address this question, we performed a series of simulations evolving cell size control networks. The size control mechanism that evolved was influenced by both cell cycle structure and specific selection pressures. Moreover, evolved networks recapitulated known size control properties of naturally occurring networks. If the mechanism is based on a G1 size control and an S/G2/M timer, as found for budding yeast and some human cells, adders likely evolve. But, if the G1 phase is significantly longer than the S/G2/M phase, as is often the case in mammalian cells in vivo, sizers become more likely. Sizers also evolve when the cell cycle structure is inverted so that G1 is a timer, while S/G2/M performs size control, as is the case for the fission yeast S. pombe. For some size control networks, cell size consistently decreases in each cycle until a burst of cell cycle inhibitor drives an extended G1 phase much like the cell division cycle of the green algae Chlamydomonas. That these size control networks evolved such self-organized criticality shows how the evolution of complex systems can drive the emergence of critical processes.
2022-04-14
bioRxiv (preprint)
doi.org