Exponentially Faster Language Modelling

Language models only really need to use an exponential fraction of their neurons for individual inferences. As proof, we present UltraFastBERT, a BERT variant that uses 0.3% of its neurons during inference while performing on par with similar BERT models. UltraFastBERT selectively engages just 12 out of 4095 neurons for each layer inference. This is achieved by replacing feedforward networks with fast feedforward networks (FFFs). While no truly efficient implementation currently exists to unlock the full acceleration potential of conditional neural execution, we provide high-level CPU code achieving 78x speedup over the optimized baseline feedforward implementation, and a PyTorch implementation delivering 40x speedup over the equivalent batched feedforward inference. We publish our training code, benchmarking setup, and model weights.

SURF: A Generalization Benchmark for GNNs Predicting Fluid Dynamics

Simulating fluid dynamics is crucial for the design and development process, ranging from simple valves to complex turbomachinery. Accurately solving the underlying physical equations is computationally expensive. Therefore, learning-based solvers that model interactions on meshes have gained interest due to their promising speed-ups. However, it is unknown to what extent these models truly understand the underlying physical principles and can generalize rather than interpolate. Generalization is a key requirement for a general-purpose fluid simulator, which should adapt to different topologies, resolutions, or thermodynamic ranges. We propose SURF, a benchmark designed to test the $\textit{generalization}$ of learned graph-based fluid simulators. SURF comprises individual datasets and provides specific performance and generalization metrics for evaluating and comparing different models. We empirically demonstrate the applicability of SURF by thoroughly investigating the two state-of-the-art graph-based models, yielding new insights into their generalization.

Flood and Echo: Algorithmic Alignment of GNNs with Distributed Computing

Graph Neural Networks are a natural fit for learning algorithms. They can directly represent tasks through an abstract but versatile graph structure and handle inputs of different sizes. This opens up the possibility for scaling and extrapolation to larger graphs, one of the most important advantages of an algorithm. However, this raises two core questions i) How can we enable nodes to gather the required information in a given graph ($\textit{information exchange}$), even if is far away and ii) How can we design an execution framework which enables this information exchange for extrapolation to larger graph sizes ($\textit{algorithmic alignment for extrapolation}$). We propose a new execution framework that is inspired by the design principles of distributed algorithms: Flood and Echo Net. It propagates messages through the entire graph in a wave like activation pattern, which naturally generalizes to larger instances. Through its sparse but parallel activations it is provably more efficient in terms of message complexity. We study the proposed model and provide both empirical evidence and theoretical insights in terms of its expressiveness, efficiency, information exchange and ability to extrapolate.

What Determines the Price of NFTs?

In the evolving landscape of digital art, Non-Fungible Tokens (NFTs) have emerged as a groundbreaking platform, bridging the realms of art and technology. NFTs serve as the foundational framework that has revolutionized the market for digital art, enabling artists to showcase and monetize their creations in unprecedented ways. NFTs combine metadata stored on the blockchain with off-chain data, such as images, to create a novel form of digital ownership. It is not fully understood how these factors come together to determine NFT prices. In this study, we analyze both on-chain and off-chain data of NFT collections trading on OpenSea to understand what influences NFT pricing. Our results show that while text and image data of the NFTs can be used to explain price variations within collections, the extracted features do not generalize to new, unseen collections. Furthermore, we find that an NFT collection's trading volume often relates to its online presence, like social media followers and website traffic.

SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning

We introduce an extension to the CLRS algorithmic learning benchmark, prioritizing scalability and the utilization of sparse representations. Many algorithms in CLRS require global memory or information exchange, mirrored in its execution model, which constructs fully connected (not sparse) graphs based on the underlying problem. Despite CLRS's aim of assessing how effectively learned algorithms can generalize to larger instances, the existing execution model becomes a significant constraint due to its demanding memory requirements and runtime (hard to scale). However, many important algorithms do not demand a fully connected graph; these algorithms, primarily distributed in nature, align closely with the message-passing paradigm employed by Graph Neural Networks. Hence, we propose SALSA-CLRS, an extension of the current CLRS benchmark specifically with scalability and sparseness in mind. Our approach includes adapted algorithms from the original CLRS benchmark and introduces new problems from distributed and randomized algorithms. Moreover, we perform a thorough empirical evaluation of our benchmark. Code is publicly available at https://github.com/jkminder/SALSA-CLRS.

Fast Feedforward Networks

We break the linear link between the layer size and its inference cost by introducing the fast feedforward (FFF) architecture, a logarithmic-time alternative to feedforward networks. We show that FFFs give comparable performance to feedforward networks at an exponential fraction of their inference cost, are quicker to deliver performance compared to mixture-of-expert networks, and can readily take the place of either in transformers. Pushing FFFs to the absolute limit, we train a vision transformer to perform single-neuron inferences at the cost of only 5.8% performance decrease against the full-width variant. Our implementation is available as a Python package; just use "pip install fastfeedforward".

An Interpretable and Attention-based Method for Gaze Estimation Using Electroencephalography

Eye movements can reveal valuable insights into various aspects of human mental processes, physical well-being, and actions. Recently, several datasets have been made available that simultaneously record EEG activity and eye movements. This has triggered the development of various methods to predict gaze direction based on brain activity. However, most of these methods lack interpretability, which limits their technology acceptance. In this paper, we leverage a large data set of simultaneously measured Electroencephalography (EEG) and Eye tracking, proposing an interpretable model for gaze estimation from EEG data. More specifically, we present a novel attention-based deep learning framework for EEG signal analysis, which allows the network to focus on the most relevant information in the signal and discard problematic channels. Additionally, we provide a comprehensive evaluation of the presented framework, demonstrating its superiority over current methods in terms of accuracy and robustness. Finally, the study presents visualizations that explain the results of the analysis and highlights the potential of attention mechanism for improving the efficiency and effectiveness of EEG data analysis in a variety of applications.

Graphtester: Exploring Theoretical Boundaries of GNNs on Graph Datasets

Graph Neural Networks (GNNs) have emerged as a powerful tool for learning from graph-structured data. However, even state-of-the-art architectures have limitations on what structures they can distinguish, imposing theoretical limits on what the networks can achieve on different datasets. In this paper, we provide a new tool called Graphtester for a comprehensive analysis of the theoretical capabilities of GNNs for various datasets, tasks, and scores. We use Graphtester to analyze over 40 different graph datasets, determining upper bounds on the performance of various GNNs based on the number of layers. Further, we show that the tool can also be used for Graph Transformers using positional node encodings, thereby expanding its scope. Finally, we demonstrate that features generated by Graphtester can be used for practical applications such as Graph Transformers, and provide a synthetic dataset to benchmark node and edge features, such as positional encodings. The package is freely available at the following URL: https://github.com/meakbiyik/graphtester.

DISCO-10M: A Large-Scale Music Dataset

Music datasets play a crucial role in advancing research in machine learning for music. However, existing music datasets suffer from limited size, accessibility, and lack of audio resources. To address these shortcomings, we present DISCO-10M, a novel and extensive music dataset that surpasses the largest previously available music dataset by an order of magnitude. To ensure high-quality data, we implement a multi-stage filtering process. This process incorporates similarities based on textual descriptions and audio embeddings. Moreover, we provide precomputed CLAP embeddings alongside DISCO-10M, facilitating direct application on various downstream tasks. These embeddings enable efficient exploration of machine learning applications on the provided data. With DISCO-10M, we aim to democratize and facilitate new research to help advance the development of novel machine learning models for music.

Siamese SIREN: Audio Compression with Implicit Neural Representations

Implicit Neural Representations (INRs) have emerged as a promising method for representing diverse data modalities, including 3D shapes, images, and audio. While recent research has demonstrated successful applications of INRs in image and 3D shape compression, their potential for audio compression remains largely unexplored. Motivated by this, we present a preliminary investigation into the use of INRs for audio compression. Our study introduces Siamese SIREN, a novel approach based on the popular SIREN architecture. Our experimental results indicate that Siamese SIREN achieves superior audio reconstruction fidelity while utilizing fewer network parameters compared to previous INR architectures.