Breaking the Context Bottleneck on Long Time Series Forecasting

Long-term time-series forecasting is essential for planning and decision-making in economics, energy, and transportation, where long foresight is required. To obtain such long foresight, models must be both efficient and effective in processing long sequence. Recent advancements have enhanced the efficiency of these models; however, the challenge of effectively leveraging longer sequences persists. This is primarily due to the tendency of these models to overfit when presented with extended inputs, necessitating the use of shorter input lengths to maintain tolerable error margins. In this work, we investigate the multiscale modeling method and propose the Logsparse Decomposable Multiscaling (LDM) framework for the efficient and effective processing of long sequences. We demonstrate that by decoupling patterns at different scales in time series, we can enhance predictability by reducing non-stationarity, improve efficiency through a compact long input representation, and simplify the architecture by providing clear task assignments. Experimental results demonstrate that LDM not only outperforms all baselines in long-term forecasting benchmarks, but also reducing both training time and memory costs.

Leveraging Language Representation for Material Recommendation, Ranking, and Exploration

Data-driven approaches for material discovery and design have been accelerated by emerging efforts in machine learning. While there is enormous progress towards learning the structure to property relationship of materials, methods that allow for general representations of crystals to effectively explore the vast material search space and identify high-performance candidates remain limited. In this work, we introduce a material discovery framework that uses natural language embeddings derived from material science-specific language models as representations of compositional and structural features. The discovery framework consists of a joint scheme that, given a query material, first recalls candidates based on representational similarity, and ranks the candidates based on target properties through multi-task learning. The contextual knowledge encoded in language representations is found to convey information about material properties and structures, enabling both similarity analysis for recall, and multi-task learning to share information for related properties. By applying the discovery framework to thermoelectric materials, we demonstrate diversified recommendations of prototype structures and identify under-studied high-performance material spaces, including halide perovskite, delafossite-like, and spinel-like structures. By leveraging material language representations, our framework provides a generalized means for effective material recommendation, which is task-agnostic and can be applied to various material systems.