[LightGBM]Upgrade lightgbmlib to v3.1.1

[zhumengzhu]

Is your feature request related to a problem? Please describe.
LightGBM has already released v3.1.1 which contains a lot of new features and performance improvement. It seems mmlspark is still using v.2.3.1(the lightgbmlib version using now is 2.3.180, not sure if it's a release of v.2.3.1).

Describe the solution you'd like
Build a jar base on v3.1.1 and deploy it into Maven central.

Additional context
I have post an issue to LightGBM but they cant' help with this because they don't own the Maven central: microsoft/LightGBM#3791 (comment).

We have a pure Java LightGBM implementation which can only do predict for binary model, and I did a simple benchmark to compare the performance between pure Java implementation and lightgbmlib-2.3.180. The result is that the Java implementation is faster. I will take some time to do a benchmark with v3.1.1 in the near future.
Here is the result:

Show JSON

 [
{
 "jmhVersion": "1.25.1",
 "benchmark": "LightGBMBenchmark.modelMicrosoftPredict",
 "mode": "avgt",
 "threads": 4,
 "forks": 1,
 "jvm": "/Library/Java/JavaVirtualMachines/jdk1.8.0_241.jdk/Contents/Home/jre/bin/java",
 "jvmArgs": [
   "-javaagent:/Users/nobody/Library/Application Support/JetBrains/Toolbox/apps/IDEA-U/ch-0/203.6682.168/IntelliJ IDEA.app/Contents/lib/idea_rt.jar=56718:/Users/nobody/Library/Application Support/JetBrains/Toolbox/apps/IDEA-U/ch-0/203.6682.168/IntelliJ IDEA.app/Contents/bin",
   "-Dfile.encoding=UTF-8"
 ],
 "jdkVersion": "1.8.0_241",
 "vmName": "Java HotSpot(TM) 64-Bit Server VM",
 "vmVersion": "25.241-b07",
 "warmupIterations": 5,
 "warmupTime": "5 s",
 "warmupBatchSize": 1,
 "measurementIterations": 5,
 "measurementTime": "5 s",
 "measurementBatchSize": 1,
 "primaryMetric": {
   "score": 0.9615637173591012,
   "scoreError": 0.41363767292155884,
   "scoreConfidence": [
     0.5479260444375423,
     1.37520139028066
   ],
   "scorePercentiles": {
     "0.0": 0.8161758376621416,
     "50.0": 0.9385292690864121,
     "90.0": 1.0905036400113504,
     "95.0": 1.0905036400113504,
     "99.0": 1.0905036400113504,
     "99.9": 1.0905036400113504,
     "99.99": 1.0905036400113504,
     "99.999": 1.0905036400113504,
     "99.9999": 1.0905036400113504,
     "100.0": 1.0905036400113504
   },
   "scoreUnit": "ms/op",
   "rawData": [
     [
       0.9385292690864121,
       0.8161758376621416,
       1.0408171273548579,
       1.0905036400113504,
       0.9217927126807438
     ]
   ]
 },
 "secondaryMetrics": {
 }
},
{
 "jmhVersion": "1.25.1",
 "benchmark": "LightGBMBenchmark.modelPredict",
 "mode": "avgt",
 "threads": 4,
 "forks": 1,
 "jvm": "/Library/Java/JavaVirtualMachines/jdk1.8.0_241.jdk/Contents/Home/jre/bin/java",
 "jvmArgs": [
   "-javaagent:/Users/nobody/Library/Application Support/JetBrains/Toolbox/apps/IDEA-U/ch-0/203.6682.168/IntelliJ IDEA.app/Contents/lib/idea_rt.jar=56718:/Users/nobody/Library/Application Support/JetBrains/Toolbox/apps/IDEA-U/ch-0/203.6682.168/IntelliJ IDEA.app/Contents/bin",
   "-Dfile.encoding=UTF-8"
 ],
 "jdkVersion": "1.8.0_241",
 "vmName": "Java HotSpot(TM) 64-Bit Server VM",
 "vmVersion": "25.241-b07",
 "warmupIterations": 5,
 "warmupTime": "5 s",
 "warmupBatchSize": 1,
 "measurementIterations": 5,
 "measurementTime": "5 s",
 "measurementBatchSize": 1,
 "primaryMetric": {
   "score": 0.24358289707023814,
   "scoreError": 0.09932042735496711,
   "scoreConfidence": [
     0.144262469715271,
     0.34290332442520527
   ],
   "scorePercentiles": {
     "0.0": 0.21786024850557864,
     "50.0": 0.24134231057091227,
     "90.0": 0.2839009022111358,
     "95.0": 0.2839009022111358,
     "99.0": 0.2839009022111358,
     "99.9": 0.2839009022111358,
     "99.99": 0.2839009022111358,
     "99.999": 0.2839009022111358,
     "99.9999": 0.2839009022111358,
     "100.0": 0.2839009022111358
   },
   "scoreUnit": "ms/op",
   "rawData": [
     [
       0.21786024850557864,
       0.22530964516359311,
       0.24134231057091227,
       0.2839009022111358,
       0.24950137889997087
     ]
   ]
 },
 "secondaryMetrics": {
 }
}
]
 ```
</details>

[welcome]

👋 Thanks for opening your first issue here! If you're reporting a 🐞 bug, please make sure you include steps to reproduce it.

[imatiach-msft]

closing as lightgbm was recently upgraded as part of this PR:
#1015
and a new jar has been released to maven:
https://mvnrepository.com/artifact/com.microsoft.ml.lightgbm/lightgbmlib/3.2.100

[imatiach-msft]

tagging @zhumengzhu