Publications

A Survey of Diversification Techniques in Search and Recommendation

Haolun Wu

Yansen Zhang

Chen Ma

Fuyuan Lyu

Bowei He

Fernando Diaz

Bhaskar Mitra

Xue (Steve) Liu

Diversifying search results is an important research topic in retrieval systems in order to satisfy both the various interests of customers … (see more)and the equal market exposure of providers. There has been a growing attention on diversity-aware research during recent years, accompanied by a proliferation of literature on methods to promote diversity in search and recommendation. However, the diversity-aware studies in retrieval systems lack a systematic organization and are rather fragmented. In this survey, we are the first to propose a unified taxonomy for classifying the metrics and approaches of diversification in both search and recommendation, which are two of the most extensively researched fields of retrieval systems. We begin the survey with a brief discussion of why diversity is important in retrieval systems, followed by a summary of the various diversity concerns in search and recommendation, highlighting their relationship and differences. For the survey’s main body, we present a unified taxonomy of diversification metrics and approaches in retrieval systems, from both the search and recommendation perspectives. In the later part of the survey, we discuss the openness research questions of diversity-aware research in search and recommendation in an effort to inspire future innovations and encourage the implementation of diversity in real-world systems.

2024-10-01

IEEE Transactions on Knowledge and Data Engineering (published)

Gintare Karolina Dziugaite

Linear Weight Interpolation Leads to Transient Performance Gains

Gaurav Iyer

David Rolnick

2024-09-28

TMLR (accepted)

A neuronal least-action principle for real-time learning in cortical circuits

Walter Senn

Dominik Dold

Akos F. Kungl

Benjamin Ellenberger

Jakob Jordan

Yoshua Bengio

João Sacramento

Mihai A. Petrovici

One of the most fundamental laws of physics is the principle of least action. Motivated by its predictive power, we introduce a neuronal lea… (see more)st-action principle for cortical processing of sensory streams to produce appropriate behavioural outputs in real time. The principle postulates that the voltage dynamics of cortical pyramidal neurons prospectively minimize the local somato-dendritic mismatch error within individual neurons. For motor output neurons, it implies minimizing an instantaneous behavioural error. For deep network neurons, it implies a prospective firing to overcome integration delays and correct for possible output errors right in time. The neuron-specific errors are extracted in the apical dendrites of pyramidal neurons through a cortical microcircuit that tries to explain away the feedback from the periphery, and correct the trajectory on the fly. Any motor output is in a moving equilibrium with the sensory inputs and the motor feedback during the whole sensory-motor trajectory. Ongoing synaptic plasticity reduces the somato-dendritic mismatch error within each cortical neuron and performs gradient descent on the output cost at any moment in time. The neuronal least-action principle offers an axiomatic framework to derive local neuronal and synaptic dynamics for global real-time computation and learning in the brain and in physical substrates in general.

2024-09-23

bioRxiv (preprint)

Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience

Manfred Diaz

Liam Paull

Andrea Tacchetti

Teacher-Student Curriculum Learning (TSCL) is a curriculum learning framework that draws inspiration from human cultural transmission and le… (see more)arning. It involves a teacher algorithm shaping the learning process of a learner algorithm by exposing it to controlled experiences. Despite its success, understanding the conditions under which TSCL is effective remains challenging. In this paper, we propose a data-centric perspective to analyze the underlying mechanics of the teacher-student interactions in TSCL. We leverage cooperative game theory to describe how the composition of the set of experiences presented by the teacher to the learner, as well as their order, influences the performance of the curriculum that is found by TSCL approaches. To do so, we demonstrate that for every TSCL problem, there exists an equivalent cooperative game, and several key components of the TSCL framework can be reinterpreted using game-theoretic principles. Through experiments covering supervised learning, reinforcement learning, and classical games, we estimate the cooperative values of experiences and use value-proportional curriculum mechanisms to construct curricula, even in cases where TSCL struggles. The framework and experimental setup we present in this work represent a novel foundation for a deeper exploration of TSCL, shedding light on its underlying mechanisms and providing insights into its broader applicability in machine learning.

2024-09-17

TMLR (accepted)

CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning

Luke Rowe

Roger Girgis

Anthony Gosselin

Bruno Carrez

Florian Golemo

Felix Heide

Liam Paull

Chris Pal

Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However… (see more), agents replayed from offline data do not react to the actions of the AV, and their behaviour cannot be easily controlled to simulate counterfactual scenarios. Existing approaches have attempted to address these shortcomings by proposing methods that rely on heuristics or learned generative models of real-world data but these approaches either lack realism or necessitate costly iterative sampling procedures to control the generated behaviours. In this work, we take an alternative approach and propose CtRL-Sim, a method that leverages return-conditioned offline reinforcement learning within a physics-enhanced Nocturne simulator to efficiently generate reactive and controllable traffic agents. Specifically, we process real-world driving data through the Nocturne simulator to generate a diverse offline reinforcement learning dataset, annotated with various reward terms. With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components. This capability enables the generation of a wide range of driving behaviours beyond the scope of the initial dataset, including those representing adversarial behaviours. We demonstrate that CtRL-Sim can efficiently generate diverse and realistic safety-critical scenarios while providing fine-grained control over agent behaviours. Further, we show that fine-tuning our model on simulated safety-critical scenarios generated by our model enhances this controllability.

2024-09-05

robot-learning.org/CoRL/2024/Conference (accepted)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Usman Anwar

Abulhair Saparov

Javier Rando

Daniel Paleka

Miles Turpin

Peter Hase

Ekdeep Singh Lubana

Erik Jenner

Stephen Casper

Oliver Sourbut

Benjamin L. Edelman

Zhaowei Zhang

Mario Günther

Anton Korinek

Jose Hernandez-Orallo

Lewis Hammond

Eric J Bigelow

Alexander Pan

Lauro Langosco

Tomasz Korbak … (see 22 more)

Heidi Chenyu Zhang

Ruiqi Zhong

Sean O hEigeartaigh

Gabriel Recchia

Giulio Corsi

Alan Chan

Markus Anderljung

Lilian Edwards

Aleksandar Petrov

Yoshua Bengio

Christian Schroeder de Witt

Danqi Chen

Sumeet Ramesh Motwani

Tegan Maharaj

Jakob Nicolaus Foerster

Philip Torr

Florian Tramèr

Samuel Albanie

Yejin Choi

David Scott Krueger

He He

Atoosa Kasirzadeh

2024-09-02

TMLR (accepted)

Audio Editing with Non-Rigid Text Prompts

Francesco Paissan

Zhepei Wang

Mirco Ravanelli

Paris Smaragdis

Cem (Yusuf) Subakan

In this paper, we explore audio-editing with non-rigid text edits. We show that the proposed editing pipeline is able to create audio edits … (see more)that remain faithful to the input audio. We explore text prompts that perform addition, style transfer, and in-painting. We quantitatively and qualitatively show that the edits are able to obtain results which outperform Audio-LDM, a recently released text-prompted audio generation model. Qualitative inspection of the results points out that the edits given by our approach remain more faithful to the input audio in terms of keeping the original onsets and offsets of the audio events.

2024-09-01

Interspeech 2024 (published)

INTREPPPID - An Orthologue-Informed Quintuplet Network for Cross-Species Prediction of Protein-Protein Interaction

Joseph Szymborski

Amin Emad

An overwhelming majority of protein-protein interaction (PPI) studies are conducted in a select few model organisms largely due to constrain… (see more)ts in time and cost of the associated “wet lab” experiments. In silico PPI inference methods are ideal tools to overcome these limitations, but often struggle with cross-species predictions. We present INTREPPPID, a method which incorporates orthology data using a new “quintuplet” neural network, which is constructed with five parallel encoders with shared parameters. INTREPPPID incorporates both a PPI classification task and an orthologous locality task. The latter learns embeddings of orthologues that have small Euclidean distances between them and large distances between embeddings of all other proteins. INTREPPPID outperforms all other leading PPI inference methods tested on both the intra-species and cross-species tasks using strict evaluation datasets. We show that INTREPPPID’s orthologous locality loss increases performance because of the biological relevance of the orthologue data, and not due to some other specious aspect of the architecture. Finally, we introduce PPI.bio and PPI Origami, a web server interface for INTREPPPID and a software tool for creating strict evaluation datasets, respectively. Together, these two initiatives aim to make both the use and development of PPI inference tools more accessible to the community. GRAPHICAL ABSTRACT

2024-08-22

Briefings in Bioinformatics (published)

One hundred years of EEG for brain and behaviour research

Faisal Mushtaq

Dominik Welke

Anne Gallagher

Yuri G. Pavlov

Layla Kouara

Jorge Bosch-Bayard

Jasper JF van den Bosch

Mahnaz Arvaneh

Amy R. Bland

Maximilien Chaumon

Cornelius Borck

Xun He

Steven J. Luck

Maro G. Machizawa

Cyril Pernet

Aina Puce

Sidney J. Segalowitz

Christine Rogers

Muhammad Awais

Claudio Babiloni … (see 75 more)

Neil W. Bailey

Sylvain Baillet

Robert C. A. Bendall

Daniel Brady

Maria L. Bringas-Vega

Niko A. Busch

Ana Calzada-Reyes

Armand Chatard

Peter E. Clayson

Michael X. Cohen

Jonathan Cole

Martin Constant

Alexandra Corneyllie

Damien Coyle

Damian Cruse

Ioannis Delis

Arnaud Delorme

Damien Fair

Tiago H. Falk

Matthias Gamer

Giorgio Ganis

Kilian Gloy

Samantha Gregory

Cameron D. Hassall

Katherine E. Hiley

Richard B. Ivry

Karim Jerbi

Michael Jenkins

Jakob Kaiser

Andreas Keil

Robert T. Knight

Silvia Kochen

Boris Kotchoubey

Olave E. Krigolson

Nicolas Langer

Heinrich R. Liesefeld

Sarah Lippé

Raquel E. London

Annmarie MacNamara

Scott Makeig

Welber Marinovic

Eduardo Martínez-Montes

Aleya A. Marzuki

Ryan K. Mathew

Christoph Michel

José d. R. Millán

Mark Mon-Williams

Lilia Morales-Chacón

Richard Naar

Gustav Nilsonne

Guiomar Niso

Erika Nyhus

Robert Oostenveld

Katharina Paul

Walter Paulus

Daniela M. Pfabigan

Gilles Pourtois

Stefan Rampp

Manuel Rausch

Kay Robbins

Paolo M. Rossini

Manuela Ruzzoli

Barbara Schmidt

Magdalena Senderecka

Narayanan Srinivasan

Yannik Stegmann

Paul M. Thompson

Mitchell Valdes-Sosa

Melle J. W. van der Molen

Domenica Veniero

Edelyn Verona

Bradley Voytek

Dezhong Yao

Alan C. Evans

Pedro Valdes-Sosa

2024-08-22

Nature Human Behaviour (published)

Zero-Shot Object-Centric Representation Learning

Aniket Rajiv Didolkar

Andrii Zadaianchuk

Anirudh Goyal

Michael Curtis Mozer

Yoshua Bengio

Georg Martius

Maximilian Seitzer

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities… (see more). Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we study current object-centric methods through the lens of zero-shot generalization by introducing a benchmark comprising eight different synthetic and real-world datasets. We analyze the factors influencing zero-shot performance and find that training on diverse real-world images improves transferability to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.

2024-08-17

ArXiv (preprint)

Sarath Chandar Anbil Parthipan

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models

Jerry Huang

Prasanna Parthasarathi

Mehdi Rezagholizadeh

2024-08-16

ArXiv (preprint)