SLAM is an important capability for many autonomous systems, and modern LiDAR-based methods offer promising performance. However, for long duration missions, existing works that either operate directly the full pointclouds or on extracted features face key tradeoffs in accuracy and computational efficiency (e.g., memory consumption). To address these issues, this paper presents DFLIOM with several key innovations. Unlike previous methods that rely on handcrafted heuristics and hand-tuned parameters for feature extraction, we propose a learning-based approach that select points relevant to LiDAR SLAM pointcloud registration. Furthermore, we extend our prior work DLIOM with the learned feature extractor and observe our method enables similar or even better localization performance using only about 20\% of the points in the dense point clouds. We demonstrate that DFLIOM performs well on multiple public benchmarks, achieving a 2.4\% decrease in localization error and 57.5\% decrease in memory usage compared to state-of-the-art methods (DLIOM). Although extracting features with the proposed network requires extra time, it is offset by the faster processing time downstream, thus maintaining real-time performance using 20Hz LiDAR on our hardware setup. The effectiveness of our learning-based feature extraction module is further demonstrated through comparison with several handcrafted feature extractors.