Long Range Arena: A Benchmark for Efficient Transformers
read the original abstract
Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often than not claiming superior or comparable model quality to vanilla Transformer models. To this date, there is no well-established consensus on how to evaluate this class of models. Moreover, inconsistent benchmarking on a wide spectrum of tasks and datasets makes it difficult to assess relative model quality amongst many models. This paper proposes a systematic and unified benchmark, LRA, specifically focused on evaluating model quality under long-context scenarios. Our benchmark is a suite of tasks consisting of sequences ranging from $1K$ to $16K$ tokens, encompassing a wide range of data types and modalities such as text, natural, synthetic images, and mathematical expressions requiring similarity, structural, and visual-spatial reasoning. We systematically evaluate ten well-established long-range Transformer models (Reformers, Linformers, Linear Transformers, Sinkhorn Transformers, Performers, Synthesizers, Sparse Transformers, and Longformers) on our newly proposed benchmark suite. LRA paves the way towards better understanding this class of efficient Transformer models, facilitates more research in this direction, and presents new challenging tasks to tackle. Our benchmark code will be released at https://github.com/google-research/long-range-arena.
This paper has not been read by Pith yet.
Forward citations
Cited by 20 Pith papers
-
Show Your Work: Scratchpads for Intermediate Computation with Language Models
Training language models to generate intermediate computation steps on a scratchpad enables them to perform multi-step tasks such as long addition and arbitrary program execution that they otherwise fail at.
-
LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
LongSpike integrates fractional-order state-space modeling into spiking neural networks, enabling better long-sequence performance than prior SNNs on LRA, WikiText-103, and Speech Commands benchmarks while retaining s...
-
PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
Stealth Pretraining Seeding plants persistent unsafe behaviors in LLMs via diffuse poisoned web content that activates on precise triggers and evades standard evaluation.
-
IE as Cache: Information Extraction Enhanced Agentic Reasoning
IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
-
Fast Cross-Operator Optimization of Attention Dataflow
MMEE encodes dataflow decisions in matrix form for fast exhaustive search, delivering 40-69% lower latency and energy use than prior methods while running 64-343x faster.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Griffin hybrid model matches Llama-2 performance while trained on over 6 times fewer tokens and offers lower inference latency with higher throughput.
-
Pretraining Recurrent Networks without Recurrence
SMT reduces RNN training to supervised learning on memory transitions (m_t, x_{t+1}) to m_{t+1} obtained from a Transformer encoder, enabling time-parallel training with O(1) gradient paths.
-
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
BMRUs enable a direct one-to-one mapping from learned parameters to current-mode analog circuit elements, with discrete hysteretic outputs suppressing noise by at least 20x and supporting sub-microwatt RNN inference i...
-
Continuity Laws for Sequential Models
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.
-
Attention-Guided Dual-Stream Learning for Group Engagement Recognition: Fusing Transformer-Encoded Motion Dynamics with Scene Context via Adaptive Gating
DualEngage fuses transformer-encoded student motion dynamics with 3D scene features via softmax-gated fusion to recognize group engagement in classroom videos, reporting 96.21% average accuracy on a university dataset.
-
Differentiable Filtering for Learning Hidden Markov Models
Belief Net learns HMM parameters by implementing the forward filter as a decoder-only neural network whose weights are the logits of the initial, transition, and emission distributions, trained end-to-end with autoreg...
-
SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.
-
The Falcon Series of Open Language Models
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
-
Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution
Introduces an LRU-based network with semantic modulation that claims to outperform prior super-resolution methods at similar computational cost.
-
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
BMRUs enable analog recurrent neural network hardware via discrete outputs that suppress noise 20-fold, with one-to-one parameter-to-circuit mapping and linear power scaling for recurrence.
-
Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count
CDLinear is a block-circulant layer achieving 1/B parameter reduction whose weight Hessian is DFT-diagonalized, yielding population condition number exactly 1 under input pre-whitening.
-
Communication Dynamics Neural Networks: FFT-Diagonalized Layers for Improved Hessian Conditioning at Reduced Parameter Count
CDLinear layers achieve population Hessian condition number exactly 1 under pre-whitening, deliver 3.8x parameter reduction versus dense layers at 0.65% accuracy cost, and show 310x better empirical conditioning on an MLP.
-
Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity
Fixed-width and decay-based attention mechanisms inspired by working memory improve Transformer grammatical accuracy and human alignment under limited training data.
-
Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba
A survey tracing the evolution of state-space models like S4 and Mamba, their efficiency trade-offs, and applications in NLP, vision, and other domains.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.