arXiv subjects

Roger Wattenhofer

Publications and source records attributed to Roger Wattenhofer.

At least 163 records · Page 9Linked to original sources

arXiv2023

Automating Rigid Origami Design

Rigid origami has shown potential in large diversity of practical applications. However, current rigid origami crease pattern design mostly relies on known tessellations. This strongly limits the diversity and novelty of patterns that can be created. In this work, we build upon the recently developed principle of three units method to formulate rigid origami design as a discrete optimization problem, the rigid origami game. Our implementation allows for a simple definition of diverse objectives and thereby expands the potential of rigid origami further to optimized, application-specific crease patterns. We showcase the flexibility of our formulation through use of a diverse set of search methods in several illustrative case studies. We are not only able to construct various patterns that approximate given target shapes, but to also specify abstract, function-based rewards which result in novel, foldable and functional designs for everyday objects.

cs.GR↗

arXiv2023

Discovering Graph Generation Algorithms

We provide a novel approach to construct generative models for graphs. Instead of using the traditional probabilistic models or deep generative models, we propose to instead find an algorithm that generates the data. We achieve this using evolutionary search and a powerful fitness function, implemented by a randomly initialized graph neural network. This brings certain advantages over current deep generative models, for instance, a higher potential for out-of-training-distribution generalization and direct interpretability, as the final graph generative process is expressed as a Python function. We show that this approach can be competitive with deep generative models and under some circumstances can even find the true graph generative process, and as such perfectly generalize.

cs.LG↗

arXiv2023

SoK: Decentralized Finance (DeFi) Attacks

Within just four years, the blockchain-based Decentralized Finance (DeFi) ecosystem has accumulated a peak total value locked (TVL) of more than 253 billion USD. This surge in DeFi's popularity has, unfortunately, been accompanied by many impactful incidents. According to our data, users, liquidity providers, speculators, and protocol operators suffered a total loss of at least 3.24 billion USD from Apr 30, 2018 to Apr 30, 2022. Given the blockchain's transparency and increasing incident frequency, two questions arise: How can we systematically measure, evaluate, and compare DeFi incidents? How can we learn from past attacks to strengthen DeFi security? In this paper, we introduce a common reference frame to systematically evaluate and compare DeFi incidents, including both attacks and accidents. We investigate 77 academic papers, 30 audit reports, and 181 real-world incidents. Our data reveals several gaps between academia and the practitioners' community. For example, few academic papers address "price oracle attacks" and "permissonless interactions", while our data suggests that they are the two most frequent incident types (15% and 10.5% correspondingly). We also investigate potential defenses, and find that: (i) 103 (56%) of the attacks are not executed atomically, granting a rescue time frame for defenders; (ii) SoTA bytecode similarity analysis can at least detect 31 vulnerable/23 adversarial contracts; and (iii) 33 (15.3%) of the adversaries leak potentially identifiable information by interacting with centralized exchanges.

cs.CR↗

arXiv2023

DeFi and NFTs Hinder Blockchain Scalability

Many classical blockchains are known to have an embarrassingly low transaction throughput, down to Bitcoin's notorious seven transactions per second limit.Various proposals and implementations for increasing throughput emerged in the first decade of blockchain research. But how much concurrency is possible? In their early days, blockchains were mostly used for simple transfers from user to user. More recently, however, decentralized finance (DeFi) and NFT marketplaces have completely changed what is happening on blockchains. Both are built using smart contracts and have gained significant popularity. Transactions on DeFi and NFT marketplaces often interact with the same smart contracts. We believe this development has transformed blockchain usage. In our work, we perform a historical analysis of Ethereum's transaction graph. We study how much interaction between transactions there was historically and how much there is now. We find that the rise of DeFi and NFT marketplaces has led to an increase in "centralization" in the transaction graph. More transactions are now interconnected: currently there are around 200 transactions per block with 4000 interdependencies between them. We further find that the parallelizability of Ethereum's current interconnected transaction workload is limited. A speedup exceeding a factor of five is currently unrealistic.

cs.CR↗

arXiv2023

Computing the Best Policy That Survives a Vote

An assembly of $n$ voters needs to decide on $t$ independent binary issues. Each voter has opinions about the issues, given by a $t$-bit vector. Anscombe's paradox shows that a policy following the majority opinion in each issue may not survive a vote by the very same set of $n$ voters, i.e., more voters may feel unrepresented by such a majority-driven policy than represented. A natural resolution is to come up with a policy that deviates a bit from the majority policy but no longer gets more opposition than support from the electorate. We show that a Hamming distance to the majority policy of at most $\lfloor (t - 1) / 2 \rfloor$ can always be guaranteed, by giving a new probabilistic argument relying on structure-preserving symmetries of the space of potential policies. Unless the electorate is evenly divided between the two options on all issues, we in fact show that a policy strictly winning the vote exists within this distance bound. Our approach also leads to a deterministic polynomial-time algorithm for finding policies with the stated guarantees, answering an open problem of previous work. For odd $t$, unless we are in the pathological case described above, we also give a simpler and more efficient algorithm running in expected polynomial time with the same guarantees. We further show that checking whether distance strictly less than $\lfloor (t - 1) /2 \rfloor$ can be achieved is NP-hard, and that checking for distance at most some input $k$ is FPT with respect to several natural parameters.

cs.GT↗

arXiv2023

DAVA: Disentangling Adversarial Variational Autoencoder

The use of well-disentangled representations offers many advantages for downstream tasks, e.g. an increased sample efficiency, or better interpretability. However, the quality of disentangled interpretations is often highly dependent on the choice of dataset-specific hyperparameters, in particular the regularization strength. To address this issue, we introduce DAVA, a novel training procedure for variational auto-encoders. DAVA completely alleviates the problem of hyperparameter selection. We compare DAVA to models with optimal hyperparameters. Without any hyperparameter tuning, DAVA is competitive on a diverse range of commonly used datasets. Underlying DAVA, we discover a necessary condition for unsupervised disentanglement, which we call PIPE. We demonstrate the ability of PIPE to positively predict the performance of downstream models in abstract reasoning. We also thoroughly investigate correlations with existing supervised and unsupervised metrics. The code is available at https://github.com/besterma/dava.

cs.LG↗

arXiv2023

The Hidden Shortcomings of (D)AOs -- An Empirical Study of On-Chain Governance

Decentralized autonomous organizations (DAOs) are a recent innovation in organizational structures, which are already widely used in the blockchain ecosystem. We empirically study the on-chain governance systems of 21 DAOs and open source the live dataset. The DAOs we study are of various size and activity, and govern a wide range of protocols and services, such as decentralized exchanges, lending protocols, infrastructure projects and common goods funding. Our analysis unveils a high concentration of voting rights, a significant hidden monetary costs of on-chain governance systems, as well as a remarkably high amount of pointless governance activity.

cs.CY↗

arXiv2023

Agent-based Graph Neural Networks

We present a novel graph neural network we call AgentNet, which is designed specifically for graph-level tasks. AgentNet is inspired by sublinear algorithms, featuring a computational complexity that is independent of the graph size. The architecture of AgentNet differs fundamentally from the architectures of traditional graph neural networks. In AgentNet, some trained \textit{neural agents} intelligently walk the graph, and then collectively decide on the output. We provide an extensive theoretical analysis of AgentNet: We show that the agents can learn to systematically explore their neighborhood and that AgentNet can distinguish some structures that are even indistinguishable by 2-WL. Moreover, AgentNet is able to separate any two graphs which are sufficiently different in terms of subgraphs. We confirm these theoretical results with synthetic experiments on hard-to-distinguish graphs and real-world graph classification tasks. In both cases, we compare favorably not only to standard GNNs but also to computationally more expensive GNN extensions.

cs.LG↗

arXiv2023

Electrode Clustering and Bandpass Analysis of EEG Data for Gaze Estimation

In this study, we validate the findings of previously published papers, showing the feasibility of an Electroencephalography (EEG) based gaze estimation. Moreover, we extend previous research by demonstrating that with only a slight drop in model performance, we can significantly reduce the number of electrodes, indicating that a high-density, expensive EEG cap is not necessary for the purposes of EEG-based eye tracking. Using data-driven approaches, we establish which electrode clusters impact gaze estimation and how the different types of EEG data preprocessing affect the models' performance. Finally, we also inspect which recorded frequencies are most important for the defined tasks.

eess.SP↗

arXiv2023

Fault-Tolerant Distributed Directories

A distributed directory is an overlay data structure on a graph $G$ that helps to access a shared token $t$. The directory supports three operations: publish, to announce the token, lookup, to read the contents of the token, and move, to get exclusive update access to the token. The directory is built upon a hierarchical partition of the graph using either weak or strong clusters. The main mechanism is the maintenance of a directory path that starts at the root node in the hierarchy and points to the current owner of the token. In the literature, there are known directory algorithms based on hierarchical graph structures, but none of them have considered failures. Given a hierarchical partition, we consider the impact of $f$ edge failures on the functionality and performance of the distributed directory. The edge failures may result in the splitting of clusters into up to $f+1$ connected components and an increase in the number of levels in the hierarchy. To recover the hierarchical partition after failures, we maintain spanning trees in the clusters and their connected components. If $G$ remains connected, we show that each level of the directory path is dilated by only a factor $f$. We also show that the performance of the publish and lookup operations is affected in the worst case by a factor $f$ with respect to the message complexity. The message complexity of the move operation increases by an $f$ factor and the number of additional layers in the hierarchy.

cs.DC↗

arXiv2023

FedHQL: Federated Heterogeneous Q-Learning

Federated Reinforcement Learning (FedRL) encourages distributed agents to learn collectively from each other's experience to improve their performance without exchanging their raw trajectories. The existing work on FedRL assumes that all participating agents are homogeneous, which requires all agents to share the same policy parameterization (e.g., network architectures and training configurations). However, in real-world applications, agents are often in disagreement about the architecture and the parameters, possibly also because of disparate computational budgets. Because homogeneity is not given in practice, we introduce the problem setting of Federated Reinforcement Learning with Heterogeneous And bLack-box agEnts (FedRL-HALE). We present the unique challenges this new setting poses and propose the Federated Heterogeneous Q-Learning (FedHQL) algorithm that principally addresses these challenges. We empirically demonstrate the efficacy of FedHQL in boosting the sample efficiency of heterogeneous agents with distinct policy parameterization using standard RL tasks.

cs.LG↗

arXiv2022

Learning Graph Algorithms With Recurrent Graph Neural Networks

Classical graph algorithms work well for combinatorial problems that can be thoroughly formalized and abstracted. Once the algorithm is derived, it generalizes to instances of any size. However, developing an algorithm that handles complex structures and interactions in the real world can be challenging. Rather than specifying the algorithm, we can try to learn it from the graph-structured data. Graph Neural Networks (GNNs) are inherently capable of working on graph structures; however, they struggle to generalize well, and learning on larger instances is challenging. In order to scale, we focus on a recurrent architecture design that can learn simple graph problems end to end on smaller graphs and then extrapolate to larger instances. As our main contribution, we identify three essential techniques for recurrent GNNs to scale. By using (i) skip connections, (ii) state regularization, and (iii) edge convolutions, we can guide GNNs toward extrapolation. This allows us to train on small graphs and apply the same model to much larger graphs during inference. Moreover, we empirically validate the extrapolation capabilities of our GNNs on algorithmic datasets.

cs.LG↗

arXiv2022

Beyond Prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations

Recent work has demonstrated that pre-trained language models (PLMs) are zero-shot learners. However, most existing zero-shot methods involve heavy human engineering or complicated self-training pipelines, hindering their application to new situations. In this work, we show that zero-shot text classification can be improved simply by clustering texts in the embedding spaces of PLMs. Specifically, we fit the unlabeled texts with a Bayesian Gaussian Mixture Model after initializing cluster positions and shapes using class names. Despite its simplicity, this approach achieves superior or comparable performance on both topic and sentiment classification datasets and outperforms prior works significantly on unbalanced datasets. We further explore the applicability of our clustering approach by evaluating it on 14 datasets with more diverse topics, text lengths, and numbers of classes. Our approach achieves an average of 20% absolute improvement over prompt-based zero-shot learning. Finally, we compare different PLM embedding spaces and find that texts are well-clustered by topics even if the PLM is not explicitly pre-trained to generate meaningful sentence embeddings. This work indicates that PLM embeddings can categorize texts without task-specific fine-tuning, thus providing a new way to analyze and utilize their knowledge and zero-shot learning ability.

cs.CL↗

arXiv2022

Exploring Price Accuracy on Uniswap V3 in Times of Distress

Financial markets have evolved over centuries, and exchanges have converged to rely on the order book mechanism for market making. Latency on the blockchain, however, has prevented decentralized exchanges (DEXes) from utilizing the order book mechanism and instead gave rise to the development of market designs that are better suited to a blockchain. Although the first widely popularized DEX, Uniswap V2, stood out through its astonishing simplicity, a recent design overhaul introduced with Uniswap V3 has introduced increasing levels of complexity aiming to increase capital efficiency. In this work, we empirically study the ability of Unsiwap V3 to handle unexpected price shocks. Our analysis finds that the prices on Uniswap V3 were inaccurate during the recent abrupt price drops of two stablecoins: UST and USDT. We identify the lack of agility required of Unsiwap V3 liquidity providers as the root cause of these worrying price inaccuracies. Additionally, we outline that there are too few incentives for liquidity providers to enter liquidity pools, given the elevated volatility in such market conditions.

q-fin.PR↗

arXiv2022

Neural Combinatorial Logic Circuit Synthesis from Input-Output Examples

We propose a novel, fully explainable neural approach to synthesis of combinatorial logic circuits from input-output examples. The carrying advantage of our method is that it readily extends to inductive scenarios, where the set of examples is incomplete but still indicative of the desired behaviour. Our method can be employed for a virtually arbitrary choice of atoms - from logic gates to FPGA blocks - as long as they can be formulated in a differentiable fashion, and consistently yields good results for synthesis of practical circuits of increasing size. In particular, we succeed in learning a number of arithmetic, bitwise, and signal-routing operations, and even generalise towards the correct behaviour in inductive scenarios. Our method, attacking a discrete logical synthesis problem with an explainable neural approach, hints at a wider promise for synthesis and reasoning-related tasks.

cs.LG↗

arXiv2022

Consensus on Demand

Digital money can be implemented efficiently by avoiding consensus. However, no-consensus implementations have drawbacks, as they cannot support smart contracts, and (even more fundamentally) they cannot deal with conflicting transactions. We present a novel protocol that combines the benefits of an asynchronous, broadcast-based digital currency, with the capacity to perform consensus. This is achieved by selectively performing consensus a posteriori, i.e., only when absolutely necessary. Our on-demand consensus comes at the price of restricting the Byzantine participants to be less than a one-fifth minority in the system, which is the optimal threshold. We formally prove the correctness of our system and present an open-source implementation, which inherits many features from the Ethereum ecosystem.

cs.DC↗

arXiv2022

A Neural Model for Regular Grammar Induction

Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computation and propose a novel neural approach to induction of regular grammars from positive and negative examples. Our model is fully explainable, its intermediate results are directly interpretable as partial parses, and it can be used to learn arbitrary regular grammars when provided with sufficient data. We find that our method consistently attains high recall and precision scores across a range of tests of varying complexity.

cs.LG↗

arXiv2022

Periodic Extrapolative Generalisation in Neural Networks

The learning of the simplest possible computational pattern -- periodicity -- is an open problem in the research of strong generalisation in neural networks. We formalise the problem of extrapolative generalisation for periodic signals and systematically investigate the generalisation abilities of classical, population-based, and recently proposed periodic architectures on a set of benchmarking tasks. We find that periodic and "snake" activation functions consistently fail at periodic extrapolation, regardless of the trainability of their periodicity parameters. Further, our results show that traditional sequential models still outperform the novel architectures designed specifically for extrapolation, and that these are in turn trumped by population-based training. We make our benchmarking and evaluation toolkit, PerKit, available and easily accessible to facilitate future work in the area.

cs.LG↗