Problem Learning: Towards the Free Will of Machines
Not on the map. Why?
Abstract (arXiv)
A machine intelligence pipeline usually consists of six components: problem, representation, model, loss, optimizer and metric. Researchers have worked hard trying to automate many components of the pipeline. However, one key component of the pipeline--problem definition--is still left mostly unexplored in terms of automation. Usually, it requires extensive efforts from domain experts to identify, define and formulate important problems in an area. However, automatically discovering research or application problems for an area is beneficial since it helps to identify valid and potentially important problems hidden in data that are unknown to domain experts, expand the scope of tasks that we can do in an area, and even inspire completely new findings. This paper describes Problem Learning, which aims at learning to discover and define valid and ethical problems from data or from the machine's interaction with the environment. We formalize problem learning as the identification of valid and ethical problems in a problem space and introduce several possible approaches to problem learning. In a broader sense, problem learning is an approach towards the free will of intelligent machines. Currently, machines are still limited to solving the problems defined by humans, without the ability or flexibility to freely explore various possible problems that are even unknown to humans. Though many machine learning techniques have been developed and integrated into intelligent systems, they still focus on the means rather than the purpose in that machines are still solving human defined problems. However, proposing good problems is sometimes even more important than solving problems, because a good problem can help to inspire new ideas and gain deeper understandings. The paper also discusses the ethical implications of problem learning under the background of Responsible AI.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 128 references that are in the map. First posted on arXiv 1 Sep 2021.
Builds on
43 of 128 references.
References · 43
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
31 more
- 2020Graph Contrastive Learning with Augmentationscited by 1,203
- 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
- 2016SPICE: Semantic Propositional Image Caption Evaluationcited by 820
- 2017Counterfactual Fairnesscited by 802
- 2016Wide & Deep Learning for Recommender Systemscited by 745
- 2016Learning to learn by gradient descent by gradient descentcited by 616
- 2017Progressive Neural Architecture Searchcited by 483
- 2017Representation Learning on Graphs: Methods and Applicationscited by 456
- 2019The many Shapley values for model explanationcited by 341
- 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
- 2016Learning to Optimizecited by 195
- 2018Fairness of Exposure in Rankingscited by 189
- 2014A Convolutional Neural Network for Modelling Sentencescited by 163
- 2019Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Searchcited by 137
- 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
- 2017Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responsescited by 98
- 2019Deep Learning vs. Traditional Computer Visioncited by 94
- 2017Beyond Parity: Fairness Objectives for Collaborative Filteringcited by 93
- 2019RecSim: A Configurable Simulation Platform for Recommender Systemscited by 91
- 2021Towards Long-term Fairness in Recommendationcited by 77
- 2021User-oriented Fairness in Recommendationcited by 75
- 2021Counterfactual Explainable Recommendationcited by 60
- 2021Personalized Transformer for Explainable Recommendationcited by 58
- 2018Learning to Evaluate Image Captioningcited by 53
- 2015Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networkscited by 46
- 2021Personalized Counterfactual Fairness in Recommendationcited by 38
- 2020Neural Collaborative Reasoningcited by 37
- 2019Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimizationcited by 28
- 2021Loss Function Discovery for Object Detection via Convergence-Simulation Driven Searchcited by 20
- 2018Multimodal Sentiment Analysis To Explore the Structure of Emotionscited by 19
- 2020Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentationcited by 16
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.