BELIEF 2024

8th International Conference on Belief Functions, 2-4 September, Belfast, United Kingdom.

Find Out More

The international conference dedicated to belief functions


The theory of belief functions, also referred to as evidence theory or Dempster-Shafer theory, was first introduced by Arthur P. Dempster in the context of statistical inference, and was later developed by Glenn Shafer as a general framework for modelling epistemic uncertainty. These early contributions have been the starting points of many important developments, including the Transferable Belief Model and the Theory of Hints. The theory of belief functions is now well established as a general framework for reasoning with uncertainty, and has well understood connections to other frameworks such as probability, possibility and imprecise probability theories.

The biennial BELIEF conferences, sponsored by the Belief Functions and Applications Society, are dedicated to the confrontation of ideas, the reporting of recent achievements and the presentation of the wide range of applications of this theory. The first edition of this conference series was held in Brest, France, in 2010, the second edition in Compiègne, France, in 2012, the third edition in Oxford, UK, in 2014, the fourth edition in Prague, Czech Republic, in 2016, the fifth edition in Compiègne, France, in 2018, the sixth edition in Shanghai, China, in 2021, and the seventh edition in Paris, France, in 2022.

The Eighth International Conference on Belief Functions (BELIEF 2024) will be held in Belfast Campus, Ulster University, Belfast, United Kingdom, on 2-4 September 2024. It will be colocated with the 23rd UK Workshop on Computational Intelligence (UKCI 2024). Participants will be able to attend presentations at both conferences. The colocation of the two events is intended to favour cross-fertilization among researchers active in both communities.

Important dates

  • 16 May 2024: Final paper submission deadline
  • 5 June 2024: Author notification
  • 18 June 2024: Camera-ready copy due

Proceedings

Proceedings of the previous editions of BELIEF have been published by Springer-Verlag as volumes of the Lecture Notes in Artificial Intelligence (LNCS/LNAI) series and indexed by: ISI Web of Science; EI Engineering Index; ACM Digital Library; dblp; Google Scholar; IO-Port; MathSciNet; Scopus; Zentralblatt MATH. Formal confirmation for the publication of this year’s proceedings will be announced soon.

IJAR Special issue

Authors of selected papers from the BELIEF 2024 conference will be invited to submit extended versions of their papers for possible inclusion in a special issue of the International Journal of Approximate Reasoning.

Author instructions

Authors should submit their papers through Microsoft CMT following the submission guideline, Springer.

The expected length of papers is no longer than 8 pages, references included, that should present original contributions with significant results.

Topics

Original contributions are solicited on theoretical aspects, but not limited to

  • Combination rules
  • Conditioning
  • Continuous belief functions
  • Independence and graphical models
  • Geometry and distance metrics
  • Mathematical foundations
  • Computational frameworks
  • Data and information fusion
  • Links with other uncertainty theories
  • Tracking and data association
  • Statistical Inference
  • Machine Learning and Pattern recognition
  • Clustering and Classification

as well as on applications to various areas including, but not limited to

  • Applications in network analysis
  • Applications in environment and climate change
  • Applications in biology and medical diagnosis
  • Applications in risk and reliability analysis
  • Applications in business and economics
  • Applications in vision and image processing

Paper Presentation and Publication

Each paper must have at least one author registered with an academic/industrial registration (i.e., not a student registration) with payment received by the author-registration deadline 18 June to avoid being withdrawn from the conference. A single, academic/industrial registration may cover up to two (2) papers. When registering, please enter the ID number(s) of the paper(s) that you will be covering with your academic/industrial registration.

If you are a student who will be presenting a paper, and you are covering that paper with your registration, then an academic/industrial registration is required for you.

BELIEF 2024 requires that each accepted paper be presented by one of the authors in person or, in case of impossibility due to, e.g., travel restrictions, online at the conference site according to the schedule published.

Any paper accepted in the technical programme, but not presented on-site or online, will be removed from the official proceedings archived by Springer.

Venue


The BELIEF 2024 Conference will take place in the BB Building of the Belfast Campus at Ulster University, in Belfast, Northern Ireland, on 2-4 September 2024. For more information about the venue, please get in the Belfast Campus of Ulster University at Belfast Campus of Ulster University



Accommodation


The local organization has secured some rooms in the following hotels, all conveniently located within walking distance of the Belfast campus of Ulster University: Ramada Belfast | Hilton Hotel Belfast | Europa Hotel

We strongly recommend participants to book their accommodations as soon as possible, given the high demand for the destination in September.

More hotels with the discounted rates can be booked directly by phone or email:

Hotel Phone Number Email
AC Hotel Belfast +44 (0) 28 95 313 180 revmgr@achotelbelfast.com
Holiday Inn Belfast City Centre +44 (0) 28 90 878 796 reservations@hibelfastcitycentre.co.uk
Hampton by Hilton +44 (0) 28 90 878 793 reservations@hbhbelfast.com
Holiday Inn Express Belfast City +44 (0) 28 90 891 894 reservations@hiexpressbelfast.com
Ibis Belfast City Centre +44 (0) 28 90 891 941 h7232-re@accor.com


Travel


Please visit the website visitbelfast.com

Programme (pdf)

(Belfast time UTC+1)

 

Instruction for oral presentation: Each presentation should last 20 minutes, including questions. The chairman is instructed to leave 15 minutes for the presentation itself and 5 minutes for questions/discussion. Presentations are oral only; no poster is required.

 

Monday, 2 September 2024
8:30 – 9:15   On-site welcome desk open (at the Buliding BD entrance, the Belfast Campus at Ulster University)
9:15 – 9:30   Conference opening - Welcome by Professor Brain Meenan, Associate Dean (Research & Innovation) of Faculty of Computing, Engineering and the Built Environment at Ulster University
9:30 – 10:30   Keynote by Zhi-Hua Zhou | A Preliminary Exploration to Learnware | Chair: Yaxin Bi
  BA-01-009, Conor Lecture Theatre of the Building BA at Ulster University, York St, Belfast BT15
11:10 – 12:30   Session 1 - Machine Learning I - BD-01-016, Building BD at the Belfast Campus - Chair: Liping Liu
11:10 – 11:30   Deep evidential clustering of images
  Loïc Guiziou, Emmanuel Ramasso, Sébastien Thibaud, Sébastien Denneulin
11:30 – 11:50   Incremental Belief-peaks Evidential Clustering
  Chaoyu Gong, Sihan Wang, Zhi-gang Su
11:50 – 12:10   Imprecise Deep Networks for Uncertain Image Classification
  Zuowei Zhang, Chuanqi Liu, Zechao Liu, Liangbo Ning, Zhunga Liu
12:10 – 12:30   Dempster-Shafer Credal Probabilistic Circuits
  David Ricardo Montalvan Hernandez, Cassio de Campos,Thomas Krak
13:30 – 14:50   Session 2 - Machine Learning II - BD-01-016, Building BD at the Belfast Campus - Chair: Rui Wang
13:30 – 13:50   Uncertainty quantification in regression neural networks using likelihood-based belief functions
  Thierry Denœux
13:50 – 14:10   An evidential time-to-event prediction model based on Gaussian random fuzzy numbers
  Ling Huang, Yucheng Xing, Thierry Denœux, Mengling Feng
14:10 – 14:30   Object Hallucination Detection in Large Vision Language Models via Evidential Conflict
  Zhekun Liu, Tao Huang, Rui Wang, Liping Jing
14:30 – 14:50   Multi-oversampling with evidence fusion for imbalanced data classification
  Hongpeng Tian, Zuowei Zhang, Zhunga Liu
15:20 – 16:20   Session 3 - Machine Learning III - BD-01-016, Building BD at the Belfast Campus - Chair: Sébastien Ramel
15:20 – 15:40   An Evidence-based Framework For Heterogeneous Electronic Health Records: A Case Study In Mortality Prediction
  Yucheng Ruan, Ling Huang, Qianyi Xu, Mengling Feng
15:40 – 16:00   Conflict Management in a Distance to Prototype-Based Evidential Deep Learning
  Danut-Vasile V Giurgi, Mihreteab N Geletu, Thomas Josso-Laurain, Maxime Devanne, Jean-Phillippe Lauffenburger, Mengesha Mamo Wogari, Jean Dezert
16:00 – 16:20   A Novel Privacy Preserving Framework for Training Dempster Shafer Theory-based Evidential Deep Neural Network
  Tu Anh Tran, Nam Huynh, Viet-Hung Dang
16:20 – 18:00   BFAS general assembly (open to conference participants)

 

Tuesday, 3 September 2024
9:30 – 10:30   Keynote by Prakash Shenoy | Knowing What You Don’t Know: Making Inferences in Incomplete Bayesian Networks | Chair: Thierry Denœux
11:00 – 12:40   Session 4 - Measures of uncertainty, conflict and distances - BD-01-016, Building BD at the Belfast Campus - Chair: Frédéric Pichon
11:00 – 11:20   A mean distance between elements of same class for richer labels
  Arthur Hoarau, Constance Thierry, Jean-Christophe Dubois, Yolande Le Gall
11:20 – 11:40   Threshold Functions and Operations in the Theory of Evidence
  Alexander Lepskiy
11:40 – 12:00   Mutual Information and Kullback-Leibler Divergence in the Dempster-Shafer Theory
  Prakash Shenoy
12:00 – 12:20   An OWA-based Distance Measure for Ordered Frames of Discernment
  Xiong Zhao, Liyao Ma, Yiyang Wang, Shuh uiBi
12:20 – 12:40   Automated hierarchical conflict reduction for crowdsourced annotation tasks using belief functions
  Constance Thierry, David Gross-Amblard, Yolande Le Gall, Jean-Christophe Dubois
13:40 – 15:20   Session 5 - Statistical Inference - BD-01-016, Building BD at the Belfast Campus - Chair: Jorge Martinez Carracedo
13:40 – 14:00   Large-sample theory for inferential models: a possibilistic Bernstein-von Mises theorem
  Ryan Martin, Jonathan P Williams
14:00 – 14:20   Variational approximations of possibilistic inferential models
  Leonardo Cella, Ryan Martin
14:20 – 14:40   Decision theory via model-free generalized fiducial inference
  Jonathan P Williams, Yang Liu
14:40 – 15:00   Which statistical hypotheses are afflicted with false confidence?
  Ryan Martin
15:00 – 15:20   Algebraic expression for the relative likelihood-based evidential prediction of an ordinal variable
  Frédéric Pichon, Sébastien Ramel
15:50 – 17:10   Session 6 - Continuous belief functions, logics, computation - BD-01-016, Building BD at the Belfast Campus - Chair: Ryan Martin
15:50 – 16:10   Gamma Belief Functions
  Liping Liu
16:10 – 16:30   Combination of Dependent Gaussian Random Fuzzy Numbers
  Thierry Denœux
16:30 – 16:50   A 3-valued Logical Foundation for Evidential Reasoning
  Chunlai Zhou
16:50 – 17:10   Accelerated Dempster Shafer using Tensor Train Representation
  Duc Truong, Erik Skau, Cassandra L Armstrong, Kari Sentz
17:20 – 18:00   Social event, Tour of the Belfast Campus

 

Wednesday, 4 September 2024
9:30 – 10:30   Keynote by Frédéric Pichon | Reliability and dependence in information fusion | Chair: Anne-Laure Jousselme
10:50 – 12:30   Session 7 - Information fusion and optimization - BD-01-016, Building BD at the Belfast Campus - Chair: Prakash Shenoy
10:50 – 11:10   Why Combining Belief Functions on Quantum Circuits?
  Qianli Zhou, Hao Luo, Eloi Bossé, Yong Deng
11:10 – 11:30   SHADED: Shapley Value-based Deceptive Evidence Detection in Belief Functions
  Haifei Zhang
11:30 – 11:50   A Novel Optimization-Based Combination Rule for Dempster-Shafer Theory
  Hasan Ihsan Turhan, Tugba Tanaydin
11:50 – 12:10   Fusing independent inferential models in a black-box manner
  Leonardo Cella
12:10 – 12:30   Optimization under Severe Uncertainty: a Generalized Minimax Regret Approach for Problems with Linear Objectives
  Tuan Anh Vu, Sohaib Afifi, Eric Lefèvre, Frédéric Pichon
13:30 – 15:30   Keynote by Robert Kozma | Sustainable Artificial Intelligence
  BA-01-009, Conor Lecture Theatre of the Building BA at Ulster University, York St, Belfast BT15 1ED
15:50 –   Conference closure

 

Keynote speakers


Zhi-Hua Zhou

Professor Zhi-Hua Zhou, Nanjing University, China

Zhi-Hua Zhou is Professor of Computer Science and Artificial Intelligence at Nanjing University. His research interests are mainly in machine learning and data mining, with significant contributions to ensemble learning, multi-label and weakly supervised learning, etc. He has authored the books "Ensemble Methods: Foundations and Algorithms", "Machine Learning", etc., and published more than 200 papers in top-tier journals or conferences. Many of his inventions have been successfully transferred to industry. He founded ACML (Asian Conference on Machine Learning), served as Program Chair for AAAI-19, IJCAI-21, etc., General Chair for ICDM'16, SDM'22, etc., and Senior Area Chair for NeurIPS and ICML. He is series editor of Springer Lecture Notes in Artificial Intelligence, on the advisory board of AI Magazine, and serves as editor-in-chief of Frontiers of Computer Science, associate editor of AIJ, MLJ, etc. He is IJCAI President, Fellow of the ACM, AAAI, AAAS, IEEE, member of the Academia Europaea, and recipient of the National Natural Science Award of China, the IEEE Computer Society Edward J. McCluskey Technical Achievement Award, the CCF-ACM Artificial Intelligence Award, etc.

Prof Zhi-Hua Zhou's talk: "Learnware = Model + Specification". This is a new proposal in machine learning, which attempts to enable users not to need to build machine learning models from scratch, with the hope of reusing small models to do things even beyond their original purposes, where the key ingredient is the specification which enables a trained model to be adequately identified to reuse according to the requirement of future users who know nothing about the model in advance. This talk will briefly introduce some preliminary research advances in this direction.


Prakash P. Shenoy

Professor Prakash P. Shenoy, University of Kansas, United States

Prakash P. Shenoy is a Distinguished Professor Emeritus in the School of Business at the University of Kansas. He was appointed Ronald G. Harper Distinguished Professor of Artificial Intelligence in 1994. His research interests are uncertain reasoning, decision analysis, and game theory. He is the inventor of valuation-based systems, an abstract framework for knowledge representation and inference that includes Bayesian probabilities, Dempster-Shafer belief functions, Spohn's kappa calculus, Zadeh's possibility theory, propositional logic, optimization, solving systems of equations, database retrieval, and other domains. He is also the co-inventor of the so-called "Shenoy-Shafer architecture" with Glenn Shafer for finding marginals of multivariate probability distributions using local computation. In 2012, with the help of Dean Neeli Bendapudi, and his colleagues in Decision Sciences, Marketing, and Finance, he formed the Center for Business Analytics Research (CBAR) in the School of Business, University of Kansas. He retired from the School of Business in August 2023 after 45 years on the faculty.

Prof Prakash Shenoy's talk: An important feature of intelligent systems is knowing what you don’t know. It is well-known that so-called generative AI systems fail in this respect. What is not so well known is that incomplete Bayes nets (with missing priors and conditionals) also fail. This is because Bayesian reasoning is unable to reason with incomplete knowledge. Using maximum entropy estimates of missing information results in point estimates for the marginals, masking the uncertainty in the marginals. Using Bayesian sensitivity analysis for the missing information (assuming it is tractable) results in incorrect intervals for the marginals. One solution is to embed an incomplete Bayes net in an equivalent Dempster-Shafer (D-S) graphical model, use belief functions to represent missing/incomplete knowledge, and then make inferences from this D-S graphical model using D-S reasoning. With complete knowledge, D-S reasoning results in the same point estimates of marginals as Bayesian reasoning. Without complete information, D-S reasoning results in intervals for the marginals of interest that accurately capture the missing information without resorting to sensitivity analysis.


Frederic Pichon

Professor Frederic Pichon, Artois University, France

Frédéric Pichon is a Full Professor at Artois University, France, where he co-leads the Decision and Information Fusion team of the Laboratory of Computer Engineering and Automation of Artois. He is a member of the Board of Directors and the treasurer of the Belief Functions and Applications Society. He is an Area Editor of the International Journal of Approximate Reasoning. He earned a Habilitation degree from Artois University in 2018. Before joining Artois University in 2013, he was a research engineer at the Decision Technologies and Mathematics Laboratory of Thales Research and Technology – a position he took in 2009 after completing his PhD under the supervision of Prof. Thierry Denœux at the University of Technology of Compiègne. His main contributions are in information fusion, classification and optimization, and are based on the theory of belief functions.

Prof Frederic Pichon's talk: Dempster's rule of combination is the cornerstone of Shafer's theory of evidence. It allows the combination of independent and reliable pieces of evidence. In this talk, extensions of Dempster's rule allowing us to account for various assumptions with respect to the reliability and dependence of the pieces of evidence, will be presented. Specifically, a general approach for the fusion of independent pieces of evidence, which permits refined forms of the lack of reliability, will first be provided. Then, a means to specify the dependence when combining reliable pieces of evidence, in the particular yet important case where they are elementary, will be described. Some theoretical as well as practical interests of these extensions will be given along the way.


Registration

Registration


Type Early Bird Registration Open Until: June 24, 2024 Registration
Academic/industrial (Regular) £325 £375
Student £225 £275


Registration fees include:
Full participation to BELIEF and UKCI conferences, including keynote presentations
BELIEF 2024 conference proceedings
Gala dinner
Welcome reception
Coffee breaks and lunches
Conference bag

Registration links and policies

On-site and online participants must register using one of the following links: Academic/industrial (Regular) | Student

Participants have to pay the suitable registration fee. Before pursuing, make sure to read carefully the payment guidelines:

  • Each attendee must register separately.
  • Please contact the committee at belief2024@bfasociety.org, if you have any doubts about your registration fee, as the payment is not refundable.
  • Please state during registration in the text field (along with the paper ID if your registration covers a paper) if you have specific food allergies or choices (e.g. vegetarian, vegan etc).
  • Student registration must be accompanied by proof of student status (e.g., student ID card); this proof must be provided to the organizers at belief2024@bfasociety.org in order to fully validate the registration.
  • Single-day conference registration fees are not available.
  • It is not possible to transfer a registration, which is personal. Changes of the name associated with a registration will not be accepted and will be treated as a new registration.

Visas and Letters of Invitation

Participants are requested to familiarize themselves with their own applicable visa requirements well in advance of the conference. Present worldwide security regulations generally result in more stringent visa requirements and associated longer visa processing time. The BELIEF 2024 organizers cannot intervene with embassies or consulates on behalf of any participant.

In order to obtain a letter of invitation for visa purposes, contact the Organizing Committee directly.

Camera-ready preparation

BELIEF 2024 Committees

General Chairs

  • Yaxin Bi, Ulster University, UK
  • Anne-Laure Jousselme, CS Group, France

Steering Committee

  • Thierry Denœux, Université de Techonlogie de Compiègne, France
  • David Mercier, Université d'Artois, France
  • Frédéric Pichon, Université d'Artois, France

Publicity Co-chairs

  • David Mercier, Université d'Artois, France
  • Anna Jurek-Loughrey, Queens' University of Belfast, UK
  • Fuyuan Xiao, Chonqing University, China

Publication Chair

  • Adrian Moore, Ulster University, UK

Local Organisation Committee

  • Naveed Khan, Ulster University, UK
  • Jorge Martinez Carracedo, Ulster University, UK
  • Colin Shewell, Ulster University, UK
  • Matias Garcia-Constantino, Ulster University, UK
  • Dr Bilal Ahmed Lodhi, Ulster University, UK
  • Fiachra Merwick, Ulster University, UK
  • Maja Pavlovic, Ulster University, UK
  • Maurice Mulvenna, Ulster University, UK
  • Jun Liu, Ulster University, UK

Programme Committee

  • Aldea Emanuel, Paris-Saclay University, France
  • Antoine Violaine, Clermont Auvergne University, France
  • Antonucci Alessandro, Dalle Molle Institute for Artificial Intelligence, Lugano, Switzerland
  • Benferhat Salem, CRIL CNRS University of Artois, France
  • Bi Yaxin, Ulster University, UK
  • Campagner Andrea, IRCCS Ospedale Galeazzi Sant'Ambrogio, Italy
  • Ciucci Davide, University of Milano Bicocca, Italy
  • Couso Ines, University of Oviedo, Spain
  • Cuzzolin Fabio, Oxford Brookes University, UK
  • Denœux Thierry, Université de Technologie de Compiègne, France
  • Destercke Sébastien, Université de Technologie de Compiègne, France
  • Elouedi Zied, Institut Supérieur de Gestion de Tunis, Tunisia
  • Fermé Eduardo, University of Madeira, Portugal
  • Fu Chao, Hefei University of Technology, China
  • Hawe Glenn Ivan, Ulster University, UK
  • Huynh Van Nam, Japan Advanced Institute of Science and Technology, Nomi, Japan
  • Jiao Lianmeng, Northwestern Polytechnical University, China
  • Jousselme Anne-Laure, CS Group, France
  • Kratochvil Vaclav, Institute of Information Theory and Automation, CAS, Prague, Czech Republic
  • Le Hégarat-Mascle Sylvie, Paris-Saclay University, France
  • Lefèvre Eric, Artois University, France
  • Lesot Marie-Jeanne, LIP6, Sorbonne University, France
  • Li Xinde, Southeast University, Nanjing, China
  • Liu Liping, University of Akron, United States
  • Liu Zhunga, Northwestern Polytechnical University, Xian, China
  • Martin Ryan, North Carolina State University, United States
  • Mercier David, Artois University, France
  • Miranda Enrique, University of Oviedo, Oviedo, Spain
  • Moral Serafin, University of Granada, Granada, Spain
  • Pichon Frédéric, Artois University, France
  • Quost Benjamin, Université de Technologie de Compiègne, France
  • Ramasso Emmanuel, FEMTO-ST, France
  • Ramel Sébastien, Artois University, France
  • Reynaud Roger, Paris-Saclay University, France
  • Shenoy Prakash, University of Kansas, USA
  • Su Zhi-gang, Southeast University, China
  • Zhou Kuang, Northwestern Polytechnical University, China