Nirav Ajmeri

Rishabh Agrawal, Nirav Ajmeri, Munindar P. Singh

Norms help regulate a society. Norms may be explicit (represented in structured form) or implicit. We address the emergence of explicit norms by developing agents who provide and reason about explanations for norm violations in deciding sanctions and identifying alternative norms. These agents use a genetic algorithm to produce norms and reinforcement learning to learn the values of these norms. We find that applying explanations leads to norms that provide better cohesion and goal satisfaction for the agents. Our results are stable for societies with differing attitudes of generosity.

Alex Davies, Nirav Ajmeri

Social network analysis faces profound difficulties in sharing data between researchers due to privacy and security concerns. A potential remedy to this issue are synthetic networks, that closely resemble their real counterparts, but can be freely distributed. generating synthetic networks requires the creation of network topologies that, in application, function as realistically as possible. Widely applied models are currently rule-based and can struggle to reproduce structural dynamics. Lead by recent developments in Graph Neural Network (GNN) models for network generation we evaluate the potential of GNNs for synthetic social networks. Our GNN use is specifically within a reasonable use-case and includes empirical evaluation using Maximum Mean Discrepancy (MMD). We include social network specific measurements which allow evaluation of how realistically synthetic networks behave in typical social network analysis applications. We find that the Gated Recurrent Attention Network (GRAN) extends well to social networks, and in comparison to a benchmark popular rule-based generation Recursive-MATrix (R-MAT) method, is better able to replicate realistic structural dynamics. We find that GRAN is more computationally costly than R-MAT, but is not excessively costly to employ, so would be effective for researchers seeking to create datasets of synthetic social networks.

Alex O. Davies, Nirav S. Ajmeri, Telmo M. Silva Filho

Large graphs are present in a variety of domains, including social networks, civil infrastructure, and the physical sciences to name a few. Graph generation is similarly widespread, with applications in drug discovery, network analysis and synthetic datasets among others. While GNN (Graph Neural Network) models have been applied in these domains their high in-memory costs restrict them to small graphs. Conversely less costly rule-based methods struggle to reproduce complex structures. We propose HIGGS (Hierarchical Generation of Graphs) as a model-agnostic framework of producing large graphs with realistic local structures. HIGGS uses GNN models with conditional generation capabilities to sample graphs in hierarchies of resolution. As a result HIGGS has the capacity to extend the scale of generated graphs from a given GNN model by quadratic order. As a demonstration we implement HIGGS using DiGress, a recent graph-diffusion model, including a novel edge-predictive-diffusion variant edge-DiGress. We use this implementation to generate categorically attributed graphs with tens of thousands of nodes. These HIGGS generated graphs are far larger than any previously produced using GNNs. Despite this jump in scale we demonstrate that the graphs produced by HIGGS are, on the local scale, more realistic than those from the rule-based model BTER.

Sz-Ting Tzeng, Nirav Ajmeri, Munindar P. Singh

We propose Exanna, a framework to realize agents that incorporate values in decision making. An Exannaagent considers the values of itself and others when providing rationales for its actions and evaluating the rationales provided by others. Via multiagent simulation, we demonstrate that considering values in decision making and producing rationales, especially for norm-deviating actions, leads to (1) higher conflict resolution, (2) better social experience, (3) higher privacy, and (4) higher flexibility.

Alex O. Davies, Riku W. Green, Nirav S. Ajmeri et al.

The principal benefit of unsupervised representation learning is that a pre-trained model can be fine-tuned where data or labels are scarce. Existing approaches for graph representation learning are domain specific, maintaining consistent node and edge features across the pre-training and target datasets. This has precluded transfer to multiple domains. We present Topology Only Pre-Training (ToP), a graph pre-training method based on node and edge feature exclusion. We show positive transfer on evaluation datasets from multiple domains, including domains not present in pre-training data, running directly contrary to assumptions made in contemporary works. On 75% of experiments, ToP models perform significantly $p \leq 0.01$ better than a supervised baseline. Performance is significantly positive on 85.7% of tasks when node and edge features are used in fine-tuning. We further show that out-of-domain topologies can produce more useful pre-training than in-domain. Under ToP we show better transfer from non-molecule pre-training, compared to molecule pre-training, on 79% of molecular benchmarks. Against the limited set of other generalist graph models ToP performs strongly, including against models with many orders of magnitude larger. These findings show that ToP opens broad areas of research in both transfer learning on scarcely populated graph domains and in graph foundation models.

Sz-Ting Tzeng, Nirav Ajmeri, Munindar P. Singh

A multiagent system is a society of autonomous agents whose interactions can be regulated via social norms. In general, the norms of a society are not hardcoded but emerge from the agents' interactions. Specifically, how the agents in a society react to each other's behavior and respond to the reactions of others determines which norms emerge in the society. We think of these reactions by an agent to the satisfactory or unsatisfactory behaviors of another agent as communications from the first agent to the second agent. Understanding these communications is a kind of social intelligence: these communications provide natural drivers for norm emergence by pushing agents toward certain behaviors, which can become established as norms. Whereas it is well-known that sanctioning can lead to the emergence of norms, we posit that a broader kind of social intelligence can prove more effective in promoting cooperation in a multiagent system. Accordingly, we develop Nest, a framework that models social intelligence via a wider variety of communications and understanding of them than in previous work. To evaluate Nest, we develop a simulated pandemic environment and conduct simulation experiments to compare Nest with baselines considering a combination of three kinds of social communication: sanction, tell, and hint. We find that societies formed of Nest agents achieve norms faster. Moreover, Nest agents effectively avoid undesirable consequences, which are negative sanctions and deviation from goals, and yield higher satisfaction for themselves than baseline agents despite requiring only an equivalent amount of information.

Jessica Woodgate, Paul Marshall, Nirav Ajmeri

Social norms are standards of behaviour common in a society. However, when agents make decisions without considering how others are impacted, norms can emerge that lead to the subjugation of certain agents. We present RAWL-E, a method to create ethical norm-learning agents. RAWL-E agents operationalise maximin, a fairness principle from Rawlsian ethics, in their decision-making processes to promote ethical norms by balancing societal well-being with individual goals. We evaluate RAWL-E agents in simulated harvesting scenarios. We find that norms emerging in RAWL-E agent societies enhance social welfare, fairness, and robustness, and yield higher minimum experience compared to those that emerge in agent societies that do not implement Rawlsian ethics.

Seth Bullock, Nirav Ajmeri, Mike Batty et al.

Advances in artificial intelligence (AI) have great potential to help address societal challenges that are both collective in nature and present at national or trans-national scale. Pressing challenges in healthcare, finance, infrastructure and sustainability, for instance, might all be productively addressed by leveraging and amplifying AI for national-scale collective intelligence. The development and deployment of this kind of AI faces distinctive challenges, both technical and socio-technical. Here, a research strategy for mobilising inter-disciplinary research to address these challenges is detailed and some of the key issues that must be faced are outlined.

Alex O. Davies, Roussel Nzoyem, Nirav Ajmeri et al.

Recent research has extensively studied how large language models manipulate integers in specific arithmetic tasks, and on a more fundamental level, how they represent numeric values. These previous works have found that language model embeddings can be used to reconstruct the original values, however, they do not evaluate whether language models actually model continuous values as continuous. Using expected properties of the embedding space, including linear reconstruction and principal component analysis, we show that language models not only represent numeric spaces as non-continuous but also introduce significant noise. Using models from three major providers (OpenAI, Google Gemini and Voyage AI), we show that while reconstruction is possible with high fidelity ($R^2 \geq 0.95$), principal components only explain a minor share of variation within the embedding space. This indicates that many components within the embedding space are orthogonal to the simple numeric input space. Further, both linear reconstruction and explained variance suffer with increasing decimal precision, despite the ordinal nature of the input space being fundamentally unchanged. The findings of this work therefore have implications for the many areas where embedding models are used, in-particular where high numerical precision, large magnitudes or mixed-sign values are common.

Alex O. Davies, Nirav S. Ajmeri, Telmo de Menezes e Silva Filho

Graph learning on molecules makes use of information from both the molecular structure and the features attached to that structure. Much work has been conducted on biasing either towards structure or features, with the aim that bias bolsters performance. Identifying which information source a dataset favours, and therefore how to approach learning that dataset, is an open issue. Here we propose Noise-Noise Ratio Difference (NNRD), a quantitative metric for whether there is more useful information in structure or features. By employing iterative noising on features and structure independently, leaving the other intact, NNRD measures the degradation of information in each. We employ NNRD over a range of molecular tasks, and show that it corresponds well to a loss of information, with intuitive results that are more expressive than simple performance aggregates. Our future work will focus on expanding data domains, tasks and types, as well as refining our choice of baseline model.

Daniel Collins, Conor Houghton, Nirav Ajmeri

Human social behavior is influenced by individual differences in social preferences. Social value orientation (SVO) is a measurable personality trait which indicates the relative importance an individual places on their own and on others' welfare when making decisions. SVO and other individual difference variables are strong predictors of human behavior and social outcomes. However, there are transient changes human behavior associated with emotions that are not captured by individual differences alone. Integral emotions, the emotions which arise in direct response to a decision-making scenario, have been linked to temporary shifts in decision-making preferences. In this work, we investigated the effects of moderating social preferences with integral emotions in multi-agent societies. We developed Svoie, a method for designing agents which make decisions based on established SVO policies, as well as alternative integral emotion policies in response to task outcomes. We conducted simulation experiments in a resource-sharing task environment, and compared societies of Svoie agents with societies of agents with fixed SVO policies. We find that societies of agents which adapt their behavior through integral emotions achieved similar collective welfare to societies of agents with fixed SVO policies, but with significantly reduced inequality between the welfare of agents with different SVO traits. We observed that by allowing agents to change their policy in response to task outcomes, agents can moderate their behavior to achieve greater social equality. \end{abstract}

Sz-Ting Tzeng, Nirav Ajmeri, Munindar P. Singh

Social norms characterize collective and acceptable group conducts in human society. Furthermore, some social norms emerge from interactions of agents or humans. To achieve agent autonomy and make norm satisfaction explainable, we include emotions into the normative reasoning process, which evaluates whether to comply or violate a norm. Specifically, before selecting an action to execute, an agent observes the environment and infers the state and consequences with its internal states after norm satisfaction or violation of a social norm. Both norm satisfaction and violation provoke further emotions, and the subsequent emotions affect norm enforcement. This paper investigates how modeling emotions affect the emergence and robustness of social norms via social simulation experiments. We find that an ability in agents to consider emotional responses to the outcomes of norm satisfaction and violation (1) promotes norm compliance; and (2) improves societal welfare.

Veljko Dubljević, George F. List, Jovan Milojevich et al.

The expansion of artificial intelligence (AI) and autonomous systems has shown the potential to generate enormous social good while also raising serious ethical and safety concerns. AI technology is increasingly adopted in transportation. A survey of various in-vehicle technologies found that approximately 64% of the respondents used a smartphone application to assist with their travel. The top-used applications were navigation and real-time traffic information systems. Among those who used smartphones during their commutes, the top-used applications were navigation and entertainment. There is a pressing need to address relevant social concerns to allow for the development of systems of intelligent agents that are informed and cognizant of ethical standards. Doing so will facilitate the responsible integration of these systems in society. To this end, we have applied Multi-Criteria Decision Analysis (MCDA) to develop a formal Multi-Attribute Impact Assessment (MAIA) questionnaire for examining the social and ethical issues associated with the uptake of AI. We have focused on the domain of autonomous vehicles (AVs) because of their imminent expansion. However, AVs could serve as a stand-in for any domain where intelligent, autonomous agents interact with humans, either on an individual level (e.g., pedestrians, passengers) or a societal level.

Veljko Dubljević, Sean Douglas, Jovan Milojevich et al.

Autonomous Vehicles (AVs) raise important social and ethical concerns, especially about accountability, dignity, and justice. We focus on the specific concerns arising from how AV technology will affect the lives and livelihoods of professional and semi-professional drivers. Whereas previous studies of such concerns have focused on the opinions of experts, we seek to understand these ethical and societal challenges from the perspectives of the drivers themselves. To this end, we adopted a qualitative research methodology based on semi-structured interviews. This is an established social science methodology that helps understand the core concerns of stakeholders in depth by avoiding the biases of superficial methods such as surveys. We find that whereas drivers agree with the experts that AVs will significantly impact transportation systems, they are apprehensive about the prospects for their livelihoods and dismiss the suggestions that driving jobs are unsatisfying and their profession does not merit protection. By showing how drivers differ from the experts, our study has ramifications beyond AVs to AI and other advanced technologies. Our findings suggest that qualitative research applied to the relevant, especially disempowered, stakeholders is essential to ensuring that new technologies are introduced ethically.

Mehdi Mashayekhi, Nirav Ajmeri, George F. List et al.

Multiagent systems provide a basis for developing systems of autonomous entities and thus find application in a variety of domains. We consider a setting where not only the member agents are adaptive but also the multiagent system viewed as an entity in its own right is adaptive. Specifically, the social structure of a multiagent system can be reflected in the social norms among its members. It is well recognized that the norms that arise in society are not always beneficial to its members. We focus on prosocial norms, which help achieve positive outcomes for society and often provide guidance to agents to act in a manner that takes into account the welfare of others. Specifically, we propose Cha, a framework for the emergence of prosocial norms. Unlike previous norm emergence approaches, Cha supports continual change to a system (agents may enter and leave) and dynamism (norms may change when the environment changes). Importantly, Cha agents incorporate prosocial decision making based on inequity aversion theory, reflecting an intuition of guilt arising from being antisocial. In this manner, Cha brings together two important themes in prosociality: decision making by individuals and fairness of system-level outcomes. We demonstrate via simulation that Cha can improve aggregate societal gains and fairness of outcomes.

Nirav Ajmeri, Shubham Goyal, Munindar P. Singh

Many cybersecurity breaches occur due to users not following good cybersecurity practices, chief among them being regulations for applying software patches to operating systems, updating applications, and maintaining strong passwords. We capture cybersecurity expectations on users as norms. We empirically investigate sanctioning mechanisms in promoting compliance with those norms as well as the detrimental effect of sanctions on the ability of users to complete their work. We realize these ideas in a game that emulates the decision making of workers in a research lab. Through a human-subject study, we find that whereas individual sanctions are more effective than group sanctions in achieving compliance and less detrimental on the ability of users to complete their work, individual sanctions offer significantly lower resilience especially for organizations comprising risk seekers. Our findings have implications for workforce training in cybersecurity.