ACM RecSys
ACM RecSys
  • Видео 391
  • Просмотров 309 908
FAccTRec 2023: The 6th Workshop on Responsible Recommendation
FAccTRec 2023: The 6th Workshop on Responsible Recommendation
facctrec.github.io/facctrec2023/
- Date: 2023-09-18
- Venue: Singapore and Online
- in conjunction with the RecSys 2023 recsys.acm.org/recsys23/
The FAccTRec2023 workshop is a valuable catalyst for research and community-building around fairness, accountability, transparency, and related topics in recommender systems.
You will find slides and related materials at facctrec.github.io/facctrec2023/program/
[Presentations]
00:00:07 - Opening
00:11:48 - The Next Billion: Design Choices and Stakeholder Outcomes in Multi-Stakeholder Recsys
01:08:50 - Fairness Vs. Personalization: Towards Equity in Epistemic Utility
01:27:38 - Fair and Responsibl...
Просмотров: 817

Видео

Journal Paper of the Year Awards: Leveraging affective hashtags for ranking music recommendations
Просмотров 477Год назад
RecSys 2022 by Eva Zangerle (University of Innsbruck), Chih-Ming Chen (National Chengchi University), Ming-Feng Tsai (National Chengchi University), Yi-Hsuan Yang (Academia Sinica) Mood and emotion play an important role when it comes to choosing musical tracks to listen to. In the field of music information retrieval and recommendation, emotion is considered contextual information that is hard...
Journal Paper of the Year Awards: Diversity by design in music recommender systems
Просмотров 244Год назад
RecSys 2022 by Lorenzo Porcaro (Universitat Pompeu Fabra), Carlos Castillo (Universitat Pompeu Fabra), Emilia Gómez (Universitat Pompeu Fabra) Music Recommender Systems (Music RS) are nowadays pivotal in shaping the listening experience of people all around the world. Partly driven by the commercial application of this technology, music recommendation research has gained increasing attention bo...
Journal Paper of the Year Award: Effects and challenges of using a nutrition assistance system
Просмотров 124Год назад
RecSys 2022 by Hanna Hauptmann (Utrecht University), Nadja Leipold (Technical University of Munich), Mira Madenach (Technical University of Munich), Monika Wintergerst (Technical University of Munich), Martin Lurz (Technical University of Munich), Georg Groh (Technical University of Munich), Markus Böhm (Technical University of Munich), Kurt Gedrich (Technical University of Munich), Helmut Krcm...
Journal Paper of the Year Awards: A compositional model of multi faceted trust
Просмотров 94Год назад
RecSys 2022 by Liliana Ardissono (University of Torino), Noemi Mauro (University of Torino) Trust-based recommender systems improve rating prediction with respect to Collaborative Filtering by leveraging the additional information provided by a trust network among users to deal with the cold start problem. However, they are challenged by recent studies according to which people generally percei...
Session 9: EANA: Reducing Privacy Risk on Large scale Recommendation Models
Просмотров 88Год назад
RecSys 2022 by Lin Ning (Google Research, United States), Steve Chien (Google Research, United States), Shuang Song (Google Research, United States), Mei Chen (Google, United States), Qiqi Xue (Google, United States), Devora Berlowitz (Google Research, United States) Embedding-based deep neural networks (DNNs) are widely used in large-scale recommendation systems. Differentially-private stochas...
Session 9: Timely Personalization at Peloton:System and Algorithm for Boosting Time Relevant Content
Просмотров 282Год назад
RecSys 2022 by Shayak Banerjee (Peloton Interactive, Inc., United States), Vijay Pappu (Peloton Interactive, Inc., United States), Nilothpal Talukder (Peloton Interactive, Inc., United States), Shoya Yoshida (Peloton Interactive, Inc., United States), Arnab Bhadury (Peloton Interactive, Inc., United States), Allison Schloss (Peloton Interactive, Inc., United States), Jasmine Paulino (Peloton In...
Session 9: Evaluation Framework for Cold Start Technologies in Large Scale Production Settings
Просмотров 304Год назад
RecSys 2022 by Moran Haham (Outbrain, Israel) Mitigating cold-start situations is a fundamental problem in almost any recommender system. In real-life, large-scale production systems, the challenge of optimizing the cold-start strategy is even greater. We present an end-to-end framework for evaluating and comparing different cold-start strategies. By applying this framework in Outbrain’s recomm...
Session 9: A GPU specialized Inference Parameter Server for Large Scale Deep Recommendation Models
Просмотров 151Год назад
RecSys 2022 by Yingcan Wei (NVIDIA, China), Matthias Langer (NVIDIA, China), Fan Yu (NVIDIA, China), Minseok Lee (NVIDIA, Korea, Republic of), Jie Liu (NVIDIA, China), Ji Shi (NVIDIA, China), Zehuan Wang (NVIDIA, China) Recommendation systems are of crucial importance for a variety of modern apps and web services, such as news feeds, social networks, e-commerce, search, etc. To achieve peak pre...
Session 9: An Incremental Learning framework for large scale CTR prediction
Просмотров 268Год назад
RecSys 2022 by Petros Katsileros (Deeplab, Greece), Nikiforos Mandilaras (Deeplab, Greece), Dimitrios Mallis (Deeplab, Greece), Vassilis Pitsikalis (Deeplab, Greece), Stavros Theodorakis (DeepLab, Greece), Gil Chamiel (Taboola, Israel) In this work we introduce an incremental learning framework for click-through-rate (CTR) prediction and demonstrate its effectiveness for Taboola’s massive-scale...
Session 9: Optimizing product recommendations for millions of merchants
Просмотров 475Год назад
RecSys 2022 by Kim Falk (Shopify, Canada), Chen Karako (Shopify, Canada) At Shopify, we serve product recommendations to customers across millions of merchants’ online stores. It is a challenge to provide optimized recommendations to all of these independent merchants; one model might create an overall improvement in our metrics on aggregate, but significantly degrade recommendations for some s...
Session 8: Revisiting the Performance of iALS on Item Recommendation Benchmarks
Просмотров 100Год назад
RecSys 2022 by Steffen Rendle (Google Research, United States), Walid Krichene (Google, United States), Li Zhang (Google Research, United States), Yehuda Koren (Google, Israel) Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications. iALS is known to be one of the most computationally efficient and scalable coll...
Session 8: You Say Factorization Machine, I Say Neural Network It’s All in the Activation
Просмотров 187Год назад
RecSys 2022 by Chen Almagor (The Hebrew University of Jerusalem, Israel), Yedid Hoshen (The Hebrew University of Jerusalem, Israel) In recent years, many methods for machine learning on tabular data were introduced that use either factorization machines, neural networks or both. This created a great variety of methods making it non-obvious which method should be used in practice. In this paper,...
Session 8: Dual Attentional Higher Order Factorization Machines
Просмотров 95Год назад
RecSys 2022 by Arindam Sarkar (Amazon, India), Dipankar Das (Amazon, India), Vivek Sembium (Amazon, India), Prakash Mandayam Comar (Amazon, India) Numerous problems of practical significance such as click-through rate (CTR) prediction, forecasting, tagging and so on, involve complex interaction of various user, item and context features. Manual feature engineering has been used in the past to m...
Session 8: Adversary or Friend? An adversarial Approach to Improving Recommender Systems
Просмотров 82Год назад
RecSys 2022 by Pannaga Shivaswamy (Netflix Inc, United States), Dario Garcia Garcia (Netflix, United States) Typical recommender systems models are trained to have good average performance across all users or items. In practice, this results in model performance that is good for some users but sub-optimal for many users. In this work, we consider adversarially trained machine learning models an...
Session 8: MARRS: A Framework for multi-objective risk-aware route recommendation
Просмотров 67Год назад
Session 8: MARRS: A Framework for multi-objective risk-aware route recommendation
Session 8: Fast And Accurate User Cold Start Learning Using Monte Carlo Tree Search
Просмотров 216Год назад
Session 8: Fast And Accurate User Cold Start Learning Using Monte Carlo Tree Search
Session 7: Augmenting Netflix Search with In Session Adapted Recommendations
Просмотров 311Год назад
Session 7: Augmenting Netflix Search with In Session Adapted Recommendations
Session 7: Off Policy Actor Critic for Recommender Systems
Просмотров 258Год назад
Session 7: Off Policy Actor Critic for Recommender Systems
Session 7:Self Supervised Bot Play for Transcript Free Conversational Recommendation with Rationales
Просмотров 38Год назад
Session 7:Self Supervised Bot Play for Transcript Free Conversational Recommendation with Rationales
Session 7: Streaming Session Based Recommendation: When Graph Neural Networks meet the Neighborhood
Просмотров 231Год назад
Session 7: Streaming Session Based Recommendation: When Graph Neural Networks meet the Neighborhood
Session 7: A Lightweight Transformer for Next Item Product Recommendation
Просмотров 402Год назад
Session 7: A Lightweight Transformer for Next Item Product Recommendation
Session 7: Learning to Ride a Buy-Cycle: A Hyper-Convolutional Model for Next Basket Repurchase Reco
Просмотров 90Год назад
Session 7: Learning to Ride a Buy-Cycle: A Hyper-Convolutional Model for Next Basket Repurchase Reco
Session 6: Recommendation as Language Processing RLP
Просмотров 382Год назад
Session 6: Recommendation as Language Processing RLP
Session 6: Bundle MCR: Towards Conversational Bundle Recommendation
Просмотров 77Год назад
Session 6: Bundle MCR: Towards Conversational Bundle Recommendation
Session 6: TorchRec: a PyTorch domain library for recommendation systems
Просмотров 619Год назад
Session 6: TorchRec: a PyTorch domain library for recommendation systems
Session 6: CAEN: A Hierarchically Attentive Evolution Network for Change Aware Recommendation
Просмотров 35Год назад
Session 6: CAEN: A Hierarchically Attentive Evolution Network for Change Aware Recommendation
Session 6: Global and Personalized Graphs for Heterogeneous Sequential Recommendation
Просмотров 63Год назад
Session 6: Global and Personalized Graphs for Heterogeneous Sequential Recommendation
Session 6: TinyKG:Memory Efficient Training Framework for Knowledge Graph Neural Recommender Systems
Просмотров 62Год назад
Session 6: TinyKG:Memory Efficient Training Framework for Knowledge Graph Neural Recommender Systems
Session 6: ProtoMF: Prototype based Matrix Factorization for Effective Explainable Recommendations
Просмотров 135Год назад
Session 6: ProtoMF: Prototype based Matrix Factorization for Effective Explainable Recommendations

Комментарии

  • @p-j-y-d
    @p-j-y-d 7 часов назад

    The Chilean restaurant is the best restaurant of Chile.

  • @karthikrajeshwaran1997
    @karthikrajeshwaran1997 День назад

    Nice one. Thanks for sharing this. Very helpful!

  • @ashiskumar1371
    @ashiskumar1371 Месяц назад

    The other person seems to be speaking in lowercase letter :) .Still pretty cool explanation

  • @karthikrajeshwaran1997
    @karthikrajeshwaran1997 Месяц назад

    Thanks Kim! Loved your book too.🎉

  • @karthikrajeshwaran1997
    @karthikrajeshwaran1997 Месяц назад

    Tx so much🎉

  • @karthikrajeshwaran1997
    @karthikrajeshwaran1997 Месяц назад

    Superb one🎉

  • @karthikrajeshwaran1997
    @karthikrajeshwaran1997 Месяц назад

    Brilliant one. Tx so much❤

  • @luckysun-fi1ci
    @luckysun-fi1ci 4 месяца назад

    Do you have any open source code? Where can I find it?

    • @dystop1an-7
      @dystop1an-7 11 дней назад

      Have you achieved it? Can you share the resources? Thank you very much!

    • @luckysun-fi1ci
      @luckysun-fi1ci 4 дня назад

      @@dystop1an-7 Sorry, I don't have either.

  • @djethereal99
    @djethereal99 4 месяца назад

    great tutorial!

  • @djethereal99
    @djethereal99 5 месяцев назад

    Nice talk!

  • @milan20081992
    @milan20081992 6 месяцев назад

    Not sure if I agree with the arguments on slide 4 about sequence continuation vs item masking. You can use the data efficiently by using back-propagation through time for sequence continuation training method.

  • @rangervor
    @rangervor 7 месяцев назад

    This is great, thank you for sharing! Is there a github repo?

  • @luisfable
    @luisfable 7 месяцев назад

    An amazing presentation, very well explained, thank you!

  • @djethereal99
    @djethereal99 9 месяцев назад

    Excellent talk!

  • @charleswilson5187
    @charleswilson5187 11 месяцев назад

    😳 Promo sm

  • @wangzichen-g5x
    @wangzichen-g5x Год назад

    😶‍🌫

  • @m_ke
    @m_ke Год назад

    Will the full talk be available at some point?

  • @zyadmohamed3963
    @zyadmohamed3963 Год назад

    How could I get the material?

  • @aguntuk10
    @aguntuk10 Год назад

    could you share the link for this notebook?

  • @a-a-auwj
    @a-a-auwj Год назад

    This is pure gold!

  • @sadenb
    @sadenb Год назад

    Can anyone explain from where is he getting softmax vectors for each video ? Softmax is only one output and not k outputs. Why are we doing nearest neighbor search by doing dot product of the user vector with the "so-called" softmax vectors. Why can't we directly take top K from softmax output /

  • @buildwithmel5486
    @buildwithmel5486 Год назад

    They first 6 minutes had audio issues

  • @shouravdey2471
    @shouravdey2471 Год назад

    20:14 system architecture 24:13 feature generation 25:47 model training 28:32 online ranking/users

  • @harshikashrivastava1438
    @harshikashrivastava1438 Год назад

    Hi, How can I access public dataset for Dressipi, Thanks!

  • @Dyslexic_Neuron
    @Dyslexic_Neuron Год назад

    how do they take care of data imbalance , given clicks are just 0.5% of total impression count !

  • @joteichmann1806
    @joteichmann1806 Год назад

    amazing work- Thx

  • @SamLendle
    @SamLendle 2 года назад

    The audio on this video is extremely quiet. Is there a version anywhere with better audio?

  • @johng5295
    @johng5295 2 года назад

    Thanks in a million.Great content.

  • @johng5295
    @johng5295 2 года назад

    Thanks in a million.Great content.

  • @jamesmax7126
    @jamesmax7126 2 года назад

    「画像が不快すぎる」、

  • @djethereal99
    @djethereal99 2 года назад

    great tutorial!

  • @dongzhenhua
    @dongzhenhua 2 года назад

    important and interesting research topic

  • @breezeyang659
    @breezeyang659 2 года назад

    This workshop is about conversational recommendation, not bias issues and solutions.

  • @suyangsuyang6018
    @suyangsuyang6018 2 года назад

    sorry,i still dont understand,can you explain Pessimistic Reward Models for Off-Policy Learning in Recommendation with some simple examples?

  • @Ahmad_Alhasanat
    @Ahmad_Alhasanat 2 года назад

    The person who asked the question at the end of the presentation didn't clarify or even use simple words the first or even second time!

  • @harshavardhanasrinivasan3125
    @harshavardhanasrinivasan3125 2 года назад

    Thanks team if possible can you please share us the code and PPT

  • @karatemoscow
    @karatemoscow 2 года назад

    26:36 wtf voice?!

  • @oliviervalery1780
    @oliviervalery1780 2 года назад

    Interesting

  • @muskduh
    @muskduh 2 года назад

    Thanks for the upload

  • @AlexLeu
    @AlexLeu 2 года назад

    i don't think this video is about bias issues?

  • @angelemccaffrey778
    @angelemccaffrey778 2 года назад

    🍀 𝚙𝚛𝚘𝚖𝚘𝚜𝚖

  • @ShustrikArsk
    @ShustrikArsk 2 года назад

    Hi! Seems that the content of the video does not match the title 🤔

  • @zeshengwang6731
    @zeshengwang6731 2 года назад

    Hello, could you turn the subtitle option on? It's a little hard to follow the English, please.

  • @boudjemaboudaa6208
    @boudjemaboudaa6208 2 года назад

    Dear, could you send me this presentation in PPT or PDF forms. Thank you in advance.

  • @divyagk9156
    @divyagk9156 2 года назад

    15:24 - Recommendation Engine @H&M 2:28:00 - Size fit recommendation 3:38:00 - Fashion Recommender Systems - Julian McAuley

  • @joaomiguel-gz3hk
    @joaomiguel-gz3hk 2 года назад

    thank you youtube recommender system

  • @ryanpandora7137
    @ryanpandora7137 2 года назад

    Thanks

  • @ageofcognizance2679
    @ageofcognizance2679 2 года назад

    Thank you very much for the incredible content! Please keep uploading for those of us who have not been able to attend in person.

  • @ewertonsilvasantos297
    @ewertonsilvasantos297 2 года назад

    Where are your masks? You are indoors!

    • @florianwilhelm9939
      @florianwilhelm9939 2 года назад

      It was a 2G conference and thus masks were not needed according to the Dutch laws at that point in time.

  • @collinoverbay6352
    @collinoverbay6352 2 года назад

    Awesome lecture series, thanks!