Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFairness Preferences, Actual and Hypothetical: A Study of Crowdworker Incentives
69
0
0.0
(
0
)
Added by
Ben Hutchinson
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
How should we decide which fairness criteria or definitions to adopt in machine learning systems? To answer this question, we must study the fairness preferences of actual users of machine learning systems. Stringent parity constraints on treatment or impact can come with trade-offs, and may not even be preferred by the social groups in question (Zafar et al., 2017). Thus it might be beneficial to elicit what the groups preferences are, rather than rely on a priori defined mathematical fairness constraints. Simply asking for self-reported rankings of users is challenging because research has shown that there are often gaps between peoples stated and actual preferences(Bernheim et al., 2013). This paper outlines a research program and experimental designs for investigating these questions. Participants in the experiments are invited to perform a set of tasks in exchange for a base payment--they are told upfront that they may receive a bonus later on, and the bonus could depend on some combination of output quantity and quality. The same group of workers then votes on a bonus payment structure, to elicit preferences. The voting is hypothetical (not tied to an outcome) for half the group and actual (tied to the actual payment outcome) for the other half, so that we can understand the relation between a groups actual preferences and hypothetical (stated) preferences. Connections and lessons from fairness in machine learning are explored.
rate research
Read More
We consider settings in which we wish to incentivize myopic agents (such as Airbnb landlords, who may emphasize short-term profits and property safety) to treat arriving clients fairly, in order to prevent overall discrimination against individuals or groups. We model such settings in both classical and contextual bandit models in which the myopic agents maximize rewards according to current empirical averages, but are also amenable to exogenous payments that may cause them to alter their choices. Our notion of fairness asks that more qualified individuals are never (probabilistically) preferred over less qualified ones [Joseph et al]. We investigate whether it is possible to design inexpensive {subsidy} or payment schemes for a principal to motivate myopic agents to play fairly in all or almost all rounds. When the principal has full information about the state of the myopic agents, we show it is possible to induce fair play on every round with a subsidy scheme of total cost $o(T)$ (for the classic setting with $k$ arms, $tilde{O}(sqrt{k^3T})$, and for the $d$-dimensional linear contextual setting $tilde{O}(dsqrt{k^3 T})$). If the principal has much more limited information (as might often be the case for an external regulator or watchdog), and only observes the number of rounds in which members from each of the $k$ groups were selected, but not the empirical estimates maintained by the myopic agent, the design of such a scheme becomes more complex. We show both positive and negative results in the classic and linear bandit settings by upper and lower bounding the cost of fair subsidy schemes.
We present a framework for analysing agent incentives using causal influence diagrams. We establish that a well-known criterion for value of information is complete. We propose a new graphical criterion for value of control, establishing its soundness and completeness. We also introduce two new concepts for incentive analysis: response incentives indicate which changes in the environment affect an optimal decision, while instrumental control incentives establish whether an agent can influence its utility via a variable X. For both new concepts, we provide sound and complete graphical criteria. We show by example how these results can help with evaluating the safety and fairness of an AI system.
The use of hypothetical instead of real decision-making incentives remains under debate after decades of economic experiments. Standard incentivized experiments involve substantial monetary costs due to participants earnings and often logistic costs as well. In time preferences experiments, which involve future payments, real payments are particularly problematic. Since immediate rewards frequently have lower transaction costs than delayed rewards in experimental tasks, among other issues, (quasi)hyperbolic functional forms cannot be accurately estimated. What if hypothetical payments provide accurate data which, moreover, avoid transaction cost problems? In this paper, we test whether the use of hypothetical - versus real - payments affects the elicitation of short-term and long-term discounting in a standard multiple price list task. One-out-of-ten participants probabilistic payment schemes are also considered. We analyze data from three studies: a lab experiment in Spain, a well-powered field experiment in Nigeria, and an online extension focused on probabilistic payments. Our results indicate that paid and hypothetical time preferences are mostly the same and, therefore, that hypothetical rewards are a good alternative to real rewards. However, our data suggest that probabilistic payments are not.
Which variables does an agent have an incentive to control with its decision, and which variables does it have an incentive to respond to? We formalise these incentives, and demonstrate unique graphical criteria for detecting them in any single decision causal influence diagram. To this end, we introduce structural causal influence models, a hybrid of the influence diagram and structural causal model frameworks. Finally, we illustrate how these incentives predict agent incentives in both fairness and AI safety applications.
Proof-of-Work (PoW) is the most widely adopted incentive model in current blockchain systems, which unfortunately is energy inefficient. Proof-of-Stake (PoS) is then proposed to tackle the energy issue. The rich-get-richer concern of PoS has been heavily debated in the blockchain community. The debate is centered around the argument that whether rich miners possessing more stakes will obtain higher staking rewards and further increase their potential income in the future. In this paper, we define two types of fairness, i.e., expectational fairness and robust fairness, that are useful for answering this question. In particular, expectational fairness illustrates that the expected income of a miner is proportional to her initial investment, indicating that the expected return on investment is a constant. To better capture the uncertainty of mining outcomes, robust fairness is proposed to characterize whether the return on investment concentrates to a constant with high probability as time evolves. Our analysis shows that the classical PoW mechanism can always preserve both types of fairness as long as the mining game runs for a sufficiently long time. Furthermore, we observe that current PoS blockchains implement various incentive models and discuss three representatives, namely ML-PoS, SL-PoS and C-PoS. We find that (i) ML-PoS (e.g., Qtum and Blackcoin) preserves expectational fairness but may not achieve robust fairness, (ii) SL-PoS (e.g., NXT) does not protect any type of fairness, and (iii) C-PoS (e.g., Ethereum 2.0) outperforms ML-PoS in terms of robust fairness while still maintaining expectational fairness. Finally, massive experiments on real blockchain systems and extensive numerical simulations are performed to validate our analysis.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
