• Submissions and dates

    DA2PL accepts two kinds of submissions:

    • Long papers that will under­go a full review process, should be at most 8 pages long in a 2‑columns for­mat and sub­mit­ted before the paper sub­mis­sion deadline. 
    • Extend­ed abstracts that should be at most 2 pages long, will under­go a light review process and are intend­ed to present pre­lim­i­nary works that would not jus­ti­fy a full paper sub­mis­sion. Abstracts will be reviewed on the fly and can be sub­mit­ted up to the dead­line for giv­ing Cam­era-ready ver­sion of papers.

    While writ­ing your paper or abstract, you should fol­low the tem­plate giv­en here.

    Your paper should be sub­mit­ted on the easy­chair plat­form, to which you can con­nect by click­ing here.

    We are cur­rent­ly plan­ning on the fol­low­ing schedule:

    • May 1st: sub­mis­sions open
    • Sep­tem­ber 1st 15th (final dead­line): paper sub­mis­sion deadline
    • Sep­tem­ber 30th Octo­ber 10th: author notification
    • Novem­ber 3rd: Cam­era-ready ver­sion of papers
    • Novem­ber 17–18: Con­fer­ence

    Top­ics of inter­est include, but are not lim­it­ed to:

    • quan­ti­ta­tive and qual­i­ta­tive approach­es to mod­el­ling pref­er­ences, user feed­back and train­ing data;
    • pref­er­ence rep­re­sen­ta­tion in terms of graph­i­cal mod­els, log­i­cal for­malisms, and soft constraints;
    • deal­ing with incom­plete and uncer­tain preferences;
    • pref­er­ence aggre­ga­tion and disaggregation;
    • learn­ing util­i­ty func­tions using regres­sion-based approaches;
    • pref­er­ence elic­i­ta­tion and active learning;
    • pref­er­ence learn­ing in com­bi­na­to­r­i­al domains;
    • learn­ing rela­tion­al pref­er­ence mod­els and relat­ed regres­sion problems;
    • clas­si­fi­ca­tion prob­lems, such as ordi­nal and hier­ar­chi­cal classification;
    • induc­ing monot­o­n­ic deci­sion mod­els for pref­er­ence representation;
    • com­par­i­son of dif­fer­ent pref­er­ence learn­ing par­a­digms (e.g.,monolithic vs. decomposition);
    • rank­ing prob­lems, such as object rank­ing, instance rank­ing and label ranking;
    • com­ple­men­tar­i­ty of pref­er­ence mod­els and hybrid methods;
    • expla­na­tion of recommendations;
    • appli­ca­tions of pref­er­ence learn­ing, such as web search, infor­ma­tion retrieval, elec­tron­ic com­merce, games, per­son­al­iza­tion, rec­om­mender systems, …