J.K. Aggarwal Award: Abhinav Gupta

Human language and thought are characterized by the ability to systematically generate a potentially infinite number of complex structures (e.g., sentences) from a finite set of familiar components (e.g., words). Recent works in emergent communication have discussed the propensity of artificial agents to develop a systematically compositional language through playing co-operative referential games. The degree of structure in the input data was found to affect the compositionality of the emerged communication protocols. Thus, we explore various structural priors in multi-agent communication and propose a novel graph referential game. We compare the effect of structural inductive bias (bag-of-words, sequences and graphs) on the emergence of compositional understanding of the input concepts measured by topographic similarity and generalization to unseen combinations of familiar properties. We empirically show that graph neural networks induce a better compositional language prior and a stronger generalization to out-of-domain data. We further perform ablation studies that show the robustness of the emerged protocol in graph referential games.


Analyzing structural priors in multi-agent communication

Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compositionality. We note that most of those works have focused on communicative bandwidth as being of primary importance. While important, it is not the only contributing factor. In this paper, we investigate the learning biases that affect the efficacy and compositionality of emergent languages. Our foremost contribution is to explore how capacity of a neural network impacts its ability to learn a compositional language. We additionally introduce a set of evaluation metrics with which we analyze the learned languages. Our hypothesis is that there should be a specific range of model capacity and channel bandwidth that induces compositional structure in the resulting language and consequently encourages systematic generalization. While we empirically see evidence for the bottom of this range, we curiously do not find evidence for the top part of the range and believe that this is an open question for the community.

Capacity, Bandwidth, and Compositionality in Emergent Language Learning

**Session Chair**: prof. Walter Kropatsch

**Speaker**:
Abhinav Gupta // Towards Self-supervised Curious Robots

Carnegie Mellon University and Facebook AI Research, USA

2020 J. K. Aggarwal Prize

*“For pioneering contributions to unsupervised and self-supervised learning in computer vision and robotics.”*

![](https://assets.underline.io/uploads/markdown_image/1/image/e6a78ce27dc6192eb153b5e872e5b18c.jpg)

**Abstract**: In the last decade, we have made significant advances in the field of computer vision thanks to supervised learning. But this passive supervision of our models has now become our biggest bottleneck. In this talk, I will discuss our efforts towards scaling up and empowering visual and robotic learning via self-supervised learning. First, I will then describe how self-supervised learning can be used for passive visual representation learning. I will describe some of the pitfalls of recent approaches and ways to overcome them. Next, I will discuss how embodiment is crucial for self-supervised learning — our agents live in the physical world and need the ability to interact in the physical world. Towards this goal, I will finally present our efforts in large-scale learning of embodied agents in robotics. Finally, I will discuss how we can move from passive supervision to active exploration — the ability of agents to create their own training data.”

**Biography**: Abhinav Gupta is an Associate Professor at the Robotics Institute, Carnegie Mellon University and Research Manager at Facebook AI Research (FAIR). Abhinav's research focuses on scaling up learning by building self-supervised, lifelong and interactive learning systems. Specifically, he is interested in how self-supervised systems can effectively use data to learn visual representation, common sense and representation for actions in robots. Abhinav is a recipient of several awards including ONR Young Investigator Award, PAMI Young Researcher Award, Sloan Research Fellowship, Okawa Foundation Grant, Bosch Young Faculty Fellowship, YPO Fellowship,  IJCAI Early Career Spotlight, ICRA Best Student Paper award, and the ECCV Best Paper Runner-up Award. His research has also been featured in Newsweek, BBC, Wall Street Journal, Wired and Slashdot.



technical paper

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS 2020

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

Abhinav Gupta

3

2

SHORT BIO

Presentations

J.K. Aggarwal Award: Abhinav Gupta

Analyzing structural priors in multi-agent communication

Capacity, Bandwidth, and Compositionality in Emergent Language Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES